minor fixes

remove isAuthed
2026-04-29 03:00:45 -04:00 · 2024-12-30 11:48:16 -05:00 · 2024-12-30 11:38:23 -05:00 · 2024-12-30 11:35:41 -05:00 · 2024-12-30 11:34:18 -05:00 · 2024-12-30 11:32:58 -05:00
120 changed files with 1938 additions and 1185 deletions
@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+import os
+import re
+import sys
+from typing import Set, Tuple
+
+
+def find_version_references(directory: str) -> Tuple[Set[str], Set[str]]:
+    openhands_versions = set()
+    runtime_versions = set()
+
+    version_pattern_openhands = re.compile(r'openhands:(\d{1})\.(\d{2})')
+    version_pattern_runtime = re.compile(r'runtime:(\d{1})\.(\d{2})')
+
+    for root, _, files in os.walk(directory):
+        # Skip .git directory
+        if '.git' in root:
+            continue
+
+        for file in files:
+            if file.endswith(
+                ('.md', '.yml', '.yaml', '.txt', '.html', '.py', '.js', '.ts')
+            ):
+                file_path = os.path.join(root, file)
+                try:
+                    with open(file_path, 'r', encoding='utf-8') as f:
+                        content = f.read()
+
+                        # Find all openhands version references
+                        matches = version_pattern_openhands.findall(content)
+                        openhands_versions.update(matches)
+
+                        # Find all runtime version references
+                        matches = version_pattern_runtime.findall(content)
+                        runtime_versions.update(matches)
+                except Exception as e:
+                    print(f'Error reading {file_path}: {e}', file=sys.stderr)
+
+    return openhands_versions, runtime_versions
+
+
+def main():
+    repo_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))
+    openhands_versions, runtime_versions = find_version_references(repo_root)
+
+    exit_code = 0
+
+    if len(openhands_versions) > 1:
+        print('Error: Multiple openhands versions found:', file=sys.stderr)
+        print('Found versions:', sorted(openhands_versions), file=sys.stderr)
+        exit_code = 1
+    elif len(openhands_versions) == 0:
+        print('Warning: No openhands version references found', file=sys.stderr)
+
+    if len(runtime_versions) > 1:
+        print('Error: Multiple runtime versions found:', file=sys.stderr)
+        print('Found versions:', sorted(runtime_versions), file=sys.stderr)
+        exit_code = 1
+    elif len(runtime_versions) == 0:
+        print('Warning: No runtime version references found', file=sys.stderr)
+
+    sys.exit(exit_code)
+
+
+if __name__ == '__main__':
+    main()
@@ -53,3 +53,16 @@ jobs:
        run: pip install pre-commit==3.7.0
      - name: Run pre-commit hooks
        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+
+  # Check version consistency across documentation
+  check-version-consistency:
+    name: Check version consistency
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+      - name: Run version consistency check
+        run: .github/scripts/check_version_consistency.py
@@ -185,12 +185,17 @@ jobs:

      - name: Install OpenHands
        uses: actions/github-script@v7
+        env:
+          COMMENT_BODY: ${{ github.event.comment.body || '' }}
+          REVIEW_BODY: ${{ github.event.review.body || '' }}
+          LABEL_NAME: ${{ github.event.label.name || '' }}
+          EVENT_NAME: ${{ github.event_name }}
        with:
          script: |
-            const commentBody = `${{ github.event.comment.body || '' }}`.trim();
-            const reviewBody = `${{ github.event.review.body || '' }}`.trim();
-            const labelName = `${{ github.event.label.name || '' }}`.trim();
-            const eventName = `${{ github.event_name }}`.trim();
+            const commentBody = process.env.COMMENT_BODY.trim();
+            const reviewBody = process.env.REVIEW_BODY.trim();
+            const labelName = process.env.LABEL_NAME.trim();
+            const eventName = process.env.EVENT_NAME.trim();

            // Check conditions
            const isExperimentalLabel = labelName === "fix-me-experimental";
@@ -8,7 +8,7 @@ Otherwise, you can clone the OpenHands project directly.
 * Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
 * [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
 * [Python](https://www.python.org/downloads/) = 3.12
-* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
+* [NodeJS](https://nodejs.org/en/download/package-manager) >= 20.x
 * [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
 * OS-specific dependencies:
  - Ubuntu: build-essential => `sudo apt-get install build-essential`
@@ -81,10 +81,10 @@ check-nodejs:
 	@if command -v node > /dev/null; then \
 		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
 		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -gt 18 ] || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -gt 17 ]) || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -eq 17 ] && [ "$${NODE_VERSION_ARRAY[2]}" -ge 1 ]); then \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 20 ]; then \
 			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
 		else \
-			echo "$(RED)Node.js 18.17.1 or later is required. Please install Node.js 18.17.1 or later to continue.$(RESET)"; \
+			echo "$(RED)Node.js 20.x or later is required. Please install Node.js 20.x or later to continue.$(RESET)"; \
 			exit 1; \
 		fi; \
 	else \
@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
    --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
    -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
    -v /var/run/docker.sock:/var/run/docker.sock \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
    python -m openhands.core.cli
 ```

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
    --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
    -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
    -v /var/run/docker.sock:/var/run/docker.sock \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```
@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.

 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.16
+    docker.all-hands.dev/all-hands-ai/openhands:0.17
 ```

 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).
@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.

 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -v /var/run/docker.sock:/var/run/docker.sock \
    # ...
 ```
@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
    --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
    -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
    -v /var/run/docker.sock:/var/run/docker.sock \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
    python -m openhands.core.cli
 ```

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
    --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
    -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
    -v /var/run/docker.sock:/var/run/docker.sock \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```
@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。

 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.16
+    docker.all-hands.dev/all-hands-ai/openhands:0.17
 ```

 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。
@@ -11,7 +11,7 @@

 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
    -v /var/run/docker.sock:/var/run/docker.sock \
    # ...
 ```
@@ -12,7 +12,7 @@ To run OpenHands in headless mode with Python,
 and then run:

 ```bash
-poetry run python -m openhands.core.main -t "write a bash script that prints hi"
+poetry run python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

 You'll need to be sure to set your model, API key, and other settings via environment variables
@@ -1,14 +1,13 @@
-import useDocusaurusContext from "@docusaurus/useDocusaurusContext";
-import Layout from "@theme/Layout";
-import { HomepageHeader } from "../components/HomepageHeader/HomepageHeader";
-import { Welcome } from "../components/Welcome/Welcome";
+import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
+import Layout from '@theme/Layout';
+import { HomepageHeader } from '../components/HomepageHeader/HomepageHeader';
 import { translate } from '@docusaurus/Translate';

 export function Header({ title, summary }): JSX.Element {
  return (
    <div>
      <h1>{title}</h1>
-      <h2 style={{ fontSize: "3rem" }}>{summary}</h2>
+      <h2 style={{ fontSize: '3rem' }}>{summary}</h2>
    </div>
  );
 }
@@ -23,7 +22,7 @@ export default function Home(): JSX.Element {
        message: 'Code Less, Make More',
      })}
    >
-    <HomepageHeader />
+      <HomepageHeader />
    </Layout>
  );
 }
@@ -63,7 +63,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -43,7 +43,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-slim',
@@ -50,7 +50,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.11-bookworm',
@@ -61,7 +61,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image=BIOCODER_BENCH_CONTAINER_IMAGE,
@@ -74,7 +74,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -39,7 +39,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -124,7 +124,7 @@ def get_config(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=SandboxConfig(
            base_container_image=base_container_image,
            enable_auto_lint=True,
@@ -65,7 +65,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -50,7 +50,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -43,7 +43,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -64,7 +64,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -85,7 +85,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -48,7 +48,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='xingyaoww/od-eval-logic-reasoning:v1.0',
@@ -58,7 +58,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='xingyaoww/od-eval-miniwob:v1.0',
@@ -106,7 +106,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='xingyaoww/od-eval-mint:v1.0',
@@ -80,7 +80,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='public.ecr.aws/i5g0m1f6/ml-bench',
@@ -62,7 +62,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_budget_per_task=4,
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
@@ -76,7 +76,7 @@ def get_config(instance: pd.Series) -> AppConfig:
    )
    config = AppConfig(
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=SandboxConfig(
            base_container_image=base_container_image,
            use_host_network=False,
@@ -121,7 +121,7 @@ def get_config(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=SandboxConfig(
            base_container_image=base_container_image,
            enable_auto_lint=True,
@@ -5,7 +5,7 @@ This folder contains the evaluation harness that we built on top of the original
 The evaluation consists of three steps:

 1. Environment setup: [install python environment](../../README.md#development-environment), [configure LLM config](../../README.md#configure-openhands-and-your-llm), [launch services](https://github.com/TheAgentCompany/TheAgentCompany/blob/main/docs/SETUP.md).
-2. [Run Evaluation](#run-inference-on-the-agent-company-instances): Run all tasks and get the evaluation results.
+2. [Run Evaluation](#run-inference-on-the-agent-company-tasks): Run all tasks and get the evaluation results.

 ## Setup Environment and LLM Configuration

@@ -0,0 +1,316 @@
+###########################################################################################################
+# Adapted from https://github.com/TheAgentCompany/TheAgentCompany/blob/main/evaluation/summarise_results.py
+###########################################################################################################
+
+
+import glob
+import json
+import os
+import re
+import sys
+from typing import Dict, Tuple
+
+
+def calculate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> float:
+    """
+    Calculate the cost of the model call.
+    """
+    if 'claude-3-5-sonnet' in model.lower():
+        # https://www.anthropic.com/pricing#anthropic-api, accessed 12/11/2024
+        return 0.000003 * prompt_tokens + 0.000015 * completion_tokens
+    elif 'gpt-4o' in model.lower():
+        # https://openai.com/api/pricing/, accessed 12/11/2024
+        return 0.0000025 * prompt_tokens + 0.00001 * completion_tokens
+    elif 'gemini-1.5-pro' in model.lower():
+        # https://ai.google.dev/pricing#1_5pro, accessed 12/11/2024
+        # assuming prompts up to 128k tokens
+        cost = 0.00000125 * prompt_tokens + 0.000005 * completion_tokens
+        if prompt_tokens > 128000:
+            cost *= 2
+        return cost
+    elif 'gemini-2.0-flash-exp' in model.lower():
+        # price unknown for gemini-2.0-flash-exp, assuming same price as gemini-1.5-flash
+        cost = 0.000000075 * prompt_tokens + 0.0000003 * completion_tokens
+        if prompt_tokens > 128000:
+            cost *= 2
+        return cost
+    elif 'qwen2-72b' in model.lower():
+        # assuming hosted on Together
+        # https://www.together.ai/pricing, accessed 12/11/2024
+        return 0.0000009 * (prompt_tokens + completion_tokens)
+    elif 'qwen2p5-72b' in model.lower():
+        # assuming hosted on Together
+        # https://www.together.ai/pricing, accessed 12/14/2024
+        return 0.0000012 * (prompt_tokens + completion_tokens)
+    elif 'llama-v3p1-405b-instruct' in model.lower():
+        # assuming hosted on Fireworks AI
+        # https://fireworks.ai/pricing, accessed 12/11/2024
+        return 0.000003 * (prompt_tokens + completion_tokens)
+    elif 'llama-v3p1-70b-instruct' in model.lower():
+        # assuming hosted on Fireworks AI
+        return 0.0000009 * (prompt_tokens + completion_tokens)
+    elif 'llama-v3p3-70b-instruct' in model.lower():
+        # assuming hosted on Fireworks AI
+        return 0.0000009 * (prompt_tokens + completion_tokens)
+    elif 'amazon.nova-pro-v1:0' in model.lower():
+        # assuming hosted on Amazon Bedrock
+        # https://aws.amazon.com/bedrock/pricing/, accessed 12/11/2024
+        return 0.0000008 * prompt_tokens + 0.0000032 * completion_tokens
+    else:
+        raise ValueError(f'Unknown model: {model}')
+
+
+def analyze_eval_json_file(filepath: str) -> Tuple[int, int]:
+    """
+    Analyze a single eval JSON file and extract the total and result from final_score.
+
+    Args:
+        filepath: Path to the JSON file
+
+    Returns:
+        Tuple containing (total, result) from final_score
+    """
+    try:
+        with open(filepath, 'r') as f:
+            data = json.load(f)
+
+        final_score = data.get('final_score', {})
+        return (final_score.get('total', 0), final_score.get('result', 0))
+    except json.JSONDecodeError as e:
+        print(f'Error decoding JSON in {filepath}: {e}')
+        return (0, 0)
+    except Exception as e:
+        print(f'Error processing {filepath}: {e}')
+        return (0, 0)
+
+
+def analyze_traj_json_file(filepath: str) -> Tuple[int, float]:
+    """
+    Analyze a single trajectory JSON file and extract the steps and tokens
+    for each step. Then estimate the cost based on the tokens and the model type.
+    Note: this is assuming there's no prompt caching at all.
+    """
+    steps: int = 0
+    cost: float = 0.0
+    with open(filepath, 'r') as f:
+        data = json.load(f)
+        response_id = None
+        for action in data:
+            if 'tool_call_metadata' in action:
+                if action['tool_call_metadata']['model_response']['id'] != response_id:
+                    response_id = action['tool_call_metadata']['model_response']['id']
+                else:
+                    # openhands displays the same model response meta data multiple times, when
+                    # a single LLM call leads to multiple actions and observations.
+                    continue
+                steps += 1
+                usage = action['tool_call_metadata']['model_response']['usage']
+                model: str = action['tool_call_metadata']['model_response']['model']
+                prompt_tokens = usage['prompt_tokens']
+                completion_tokens = usage['completion_tokens']
+                cost += calculate_cost(model, prompt_tokens, completion_tokens)
+
+    return (steps, cost)
+
+
+def analyze_folder(
+    folder_path: str,
+) -> Tuple[Dict[str, Tuple[int, int]], Dict[str, Tuple[int, float]]]:
+    """
+    Analyze all eval_*.json & traj_*.json files in the specified folder.
+
+    Args:
+        folder_path: Path to the folder containing JSON files
+
+    Returns:
+        dictionaries:
+        - eval_results: Dictionary with filename as key and (total, result) tuple as value
+        - traj_results: Dictionary with filename as key and (steps, cost) tuple as value
+    """
+    eval_results = {}
+    traj_results = {}
+
+    eval_pattern = os.path.join(folder_path, 'eval_*.json')
+    traj_pattern = os.path.join(folder_path, 'traj_*.json')
+
+    for filepath in glob.glob(eval_pattern):
+        filename = os.path.basename(filepath)
+        total, result = analyze_eval_json_file(filepath)
+        key = re.search(r'eval_(.+)\.json', filename).group(1)
+        eval_results[key] = (total, result)
+
+    for filepath in glob.glob(traj_pattern):
+        filename = os.path.basename(filepath)
+        steps, cost = analyze_traj_json_file(filepath)
+        key = re.search(r'traj_(.+)\.json', filename).group(1)
+        traj_results[key] = (steps, cost)
+
+    return eval_results, traj_results
+
+
+def get_task_nature_category(task_name: str) -> str:
+    """
+    Get the nature category of the task.
+    """
+    task_nature = task_name.split('-')[0]
+    if task_nature.lower() in ['sde', 'pm', 'ds', 'admin', 'hr', 'finance']:
+        return task_nature
+    else:
+        return 'other'
+
+
+def calculate_score(total: int, result: int) -> float:
+    """
+    Calculate the score as a number between 0 and 1.
+
+    Formula: score = (result / total) * 0.5 + (result // total) * 0.5
+    Explanation:
+    - (result / total) * 0.5: This is the completion ratio, scaled down to a 0-0.5 range.
+    - (result // total) * 0.5: This is a binary score indicating whether the task was completed or not.
+
+    Args:
+        total: Total possible points
+        result: Actual points achieved
+
+    Returns:
+        Score as a number between 0 and 1
+    """
+    return (result / total * 0.5) + (result // total * 0.5)
+
+
+def is_perfect_completion(total: int, result: int) -> bool:
+    """
+    Check if the task achieved perfect completion.
+
+    Args:
+        total: Total possible points
+        result: Actual points achieved
+
+    Returns:
+        True if result equals total, False otherwise
+    """
+    return total > 0 and total == result
+
+
+def main():
+    if len(sys.argv) != 2:
+        print('Usage: poetry run python summarise_results.py <folder_path>')
+        sys.exit(1)
+
+    folder_path = sys.argv[1]
+
+    if not os.path.isdir(folder_path):
+        print(f"Error: '{folder_path}' is not a valid directory")
+        sys.exit(1)
+
+    eval_results, traj_results = analyze_folder(folder_path)
+
+    if not eval_results:
+        print(f'No eval_*.json files found in {folder_path}')
+        return
+
+    # Create list of results with completion ratios for sorting
+    detailed_results = [
+        (
+            task_name,
+            total,
+            result,
+            calculate_score(total, result),
+            is_perfect_completion(total, result),
+            get_task_nature_category(task_name),
+        )
+        for task_name, (total, result) in eval_results.items()
+    ]
+
+    # Sort by score in descending order
+    detailed_results.sort(key=lambda x: (-x[3], x[0]))
+
+    # Calculate perfect completion stats
+    perfect_completions = sum(
+        1 for _, _, _, _, is_perfect, _ in detailed_results if is_perfect
+    )
+
+    # Print header
+    print('\n# Evaluation Results Report')
+    print('\n## Results per File')
+    print('\n*Sorted by score (⭐ indicates perfect completion)*\n')
+
+    # Print table header
+    print(
+        '| Filename | Total | Result | Score | Steps | Cost (assuming no prompt caching)|'
+    )
+    print('|----------|--------|---------|-------|-------|------|')
+
+    # Print individual file results
+    for task_name, total, result, score, is_perfect, task_nature in detailed_results:
+        perfect_marker = ' ⭐' if is_perfect else ''
+        print(
+            f'| {task_name} | {total:,} | {result:,} | {score:.2f}{perfect_marker} | {traj_results[task_name][0]} | {traj_results[task_name][1]:.2f} |'
+        )
+
+    # Print summary section
+    print('\n## Summary\n')
+    print(f'**Tasks Evaluated:** {len(eval_results)}\n')
+    print(
+        f'**Perfect Completions:** {perfect_completions}/{len(eval_results)} ({(perfect_completions/len(eval_results)*100):.2f}%)\n'
+    )
+
+    overall_score = (
+        sum(score for _, _, _, score, _, _ in detailed_results)
+        / len(detailed_results)
+        * 100
+    )
+    avg_steps = sum(steps for steps, _ in traj_results.values()) / len(traj_results)
+    avg_cost = sum(cost for _, cost in traj_results.values()) / len(traj_results)
+    print(f'**Overall Score:** {overall_score:.2f}%\n')
+    print(f'**Average Steps:** {avg_steps:.2f}\n')
+    print(f'**Average Cost (USD):** {avg_cost:.2f}\n')
+
+    # Additional statistics
+    if detailed_results:
+        highest_score = max(score for _, _, _, score, _, _ in detailed_results)
+        lowest_score = min(score for _, _, _, score, _, _ in detailed_results)
+        median_score = detailed_results[len(detailed_results) // 2][3]
+        avg_score = sum(score for _, _, _, score, _, _ in detailed_results) / len(
+            detailed_results
+        )
+
+        print('\n## Statistics\n')
+        print('| Metric | Value |')
+        print('|---------|--------|')
+        print(f'| Highest Task Score | {highest_score*100:.2f}% |')
+        print(f'| Lowest Task Score | {lowest_score*100:.2f}% |')
+        print(f'| Median Task Score | {median_score*100:.2f}% |')
+        print(f'| Average Task Score | {avg_score*100:.2f}% |')
+
+        # compute avg score per nature category
+        print('\n## Statistics per Nature Category\n')
+        print('| Metric | Value |')
+        print('|---------|--------|')
+        for task_nature in ['sde', 'pm', 'ds', 'admin', 'hr', 'finance', 'other']:
+            num_of_tasks = sum(
+                1
+                for _, _, _, _, _, nature_category in detailed_results
+                if nature_category == task_nature
+            )
+            task_nature_score = (
+                sum(
+                    score
+                    for _, _, _, score, _, nature_category in detailed_results
+                    if nature_category == task_nature
+                )
+                / num_of_tasks
+            )
+            perfect_completions = sum(
+                1
+                for _, _, _, _, is_perfect, nature_category in detailed_results
+                if nature_category == task_nature and is_perfect
+            )
+            print(
+                f'| Perfect Completions for {task_nature} | {perfect_completions}/{num_of_tasks} ({perfect_completions/num_of_tasks*100:.2f}%) |'
+            )
+            print(f'| Average Score for {task_nature} | {task_nature_score*100:.2f}% |')
+
+
+if __name__ == '__main__':
+    main()
@@ -44,7 +44,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -53,7 +53,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
@@ -42,7 +42,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            # use default base_container_image
@@ -0,0 +1,47 @@
+import { describe, expect, it, vi } from "vitest";
+import { retrieveLatestGitHubCommit } from "../../src/api/github";
+
+describe("retrieveLatestGitHubCommit", () => {
+  const { githubGetMock } = vi.hoisted(() => ({
+    githubGetMock: vi.fn(),
+  }));
+
+  vi.mock("../../src/api/github-axios-instance", () => ({
+    github: {
+      get: githubGetMock,
+    },
+  }));
+
+  it("should return the latest commit when repository has commits", async () => {
+    const mockCommit = {
+      sha: "123abc",
+      commit: {
+        message: "Initial commit",
+      },
+    };
+
+    githubGetMock.mockResolvedValueOnce({
+      data: [mockCommit],
+    });
+
+    const result = await retrieveLatestGitHubCommit("user/repo");
+    expect(result).toEqual(mockCommit);
+  });
+
+  it("should return null when repository is empty", async () => {
+    const error = new Error("Repository is empty");
+    (error as any).response = { status: 409 };
+    githubGetMock.mockRejectedValueOnce(error);
+
+    const result = await retrieveLatestGitHubCommit("user/empty-repo");
+    expect(result).toBeNull();
+  });
+
+  it("should throw error for other error cases", async () => {
+    const error = new Error("Network error");
+    (error as any).response = { status: 500 };
+    githubGetMock.mockRejectedValueOnce(error);
+
+    await expect(retrieveLatestGitHubCommit("user/repo")).rejects.toThrow();
+  });
+});
@@ -28,8 +28,8 @@ describe("AccountSettingsContextMenu", () => {
    expect(
      screen.getByTestId("account-settings-context-menu"),
    ).toBeInTheDocument();
-    expect(screen.getByText("Account Settings")).toBeInTheDocument();
-    expect(screen.getByText("Logout")).toBeInTheDocument();
+    expect(screen.getByText("ACCOUNT_SETTINGS$SETTINGS")).toBeInTheDocument();
+    expect(screen.getByText("ACCOUNT_SETTINGS$LOGOUT")).toBeInTheDocument();
  });

  it("should call onClickAccountSettings when the account settings option is clicked", async () => {
@@ -42,7 +42,7 @@ describe("AccountSettingsContextMenu", () => {
      />,
    );

-    const accountSettingsOption = screen.getByText("Account Settings");
+    const accountSettingsOption = screen.getByText("ACCOUNT_SETTINGS$SETTINGS");
    await user.click(accountSettingsOption);

    expect(onClickAccountSettingsMock).toHaveBeenCalledOnce();
@@ -58,7 +58,7 @@ describe("AccountSettingsContextMenu", () => {
      />,
    );

-    const logoutOption = screen.getByText("Logout");
+    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
    await user.click(logoutOption);

    expect(onLogoutMock).toHaveBeenCalledOnce();
@@ -74,7 +74,7 @@ describe("AccountSettingsContextMenu", () => {
      />,
    );

-    const logoutOption = screen.getByText("Logout");
+    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
    await user.click(logoutOption);

    expect(onLogoutMock).not.toHaveBeenCalled();
@@ -90,7 +90,7 @@ describe("AccountSettingsContextMenu", () => {
      />,
    );

-    const accountSettingsButton = screen.getByText("Account Settings");
+    const accountSettingsButton = screen.getByText("ACCOUNT_SETTINGS$SETTINGS");
    await user.click(accountSettingsButton);
    await user.click(document.body);

@@ -58,7 +58,7 @@ describe("UserActions", () => {
    const userAvatar = screen.getByTestId("user-avatar");
    await user.click(userAvatar);

-    const accountSettingsOption = screen.getByText("Account Settings");
+    const accountSettingsOption = screen.getByText("ACCOUNT_SETTINGS$SETTINGS");
    await user.click(accountSettingsOption);

    expect(onClickAccountSettingsMock).toHaveBeenCalledOnce();
@@ -79,7 +79,7 @@ describe("UserActions", () => {
    const userAvatar = screen.getByTestId("user-avatar");
    await user.click(userAvatar);

-    const logoutOption = screen.getByText("Logout");
+    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
    await user.click(logoutOption);

    expect(onLogoutMock).toHaveBeenCalledOnce();
@@ -99,7 +99,7 @@ describe("UserActions", () => {
    const userAvatar = screen.getByTestId("user-avatar");
    await user.click(userAvatar);

-    const logoutOption = screen.getByText("Logout");
+    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
    await user.click(logoutOption);

    expect(onLogoutMock).not.toHaveBeenCalled();
@@ -8,13 +8,13 @@
      "name": "openhands-frontend",
      "version": "0.17.0",
      "dependencies": {
-        "@monaco-editor/react": "^4.6.0",
+        "@monaco-editor/react": "^4.7.0-rc.0",
        "@nextui-org/react": "^2.6.10",
        "@react-router/node": "^7.1.1",
        "@react-router/serve": "^7.1.1",
        "@react-types/shared": "^3.25.0",
        "@reduxjs/toolkit": "^2.5.0",
-        "@tanstack/react-query": "^5.62.10",
+        "@tanstack/react-query": "^5.62.11",
        "@vitejs/plugin-react": "^4.3.2",
        "@xterm/addon-fit": "^0.10.0",
        "@xterm/xterm": "^5.4.0",
@@ -27,12 +27,12 @@
        "isbot": "^5.1.19",
        "jose": "^5.9.4",
        "monaco-editor": "^0.52.2",
-        "posthog-js": "^1.203.1",
-        "react": "^18.3.1",
-        "react-dom": "^18.3.1",
+        "posthog-js": "^1.203.2",
+        "react": "^19.0.0",
+        "react-dom": "^19.0.0",
        "react-highlight": "^0.15.0",
        "react-hot-toast": "^2.4.1",
-        "react-i18next": "^15.2.0",
+        "react-i18next": "^15.4.0",
        "react-icons": "^5.4.0",
        "react-markdown": "^9.0.1",
        "react-redux": "^9.2.0",
@@ -43,7 +43,7 @@
        "sirv-cli": "^3.0.0",
        "socket.io-client": "^4.8.1",
        "tailwind-merge": "^2.6.0",
-        "vite": "^5.4.9",
+        "vite": "^5.4.11",
        "web-vitals": "^3.5.2",
        "ws": "^8.18.0"
      },
@@ -56,8 +56,8 @@
        "@testing-library/react": "^16.1.0",
        "@testing-library/user-event": "^14.5.2",
        "@types/node": "^22.10.2",
-        "@types/react": "^18.3.11",
-        "@types/react-dom": "^18.3.0",
+        "@types/react": "^19.0.2",
+        "@types/react-dom": "^19.0.2",
        "@types/react-highlight": "^0.12.8",
        "@types/react-syntax-highlighter": "^15.5.13",
        "@types/ws": "^8.5.12",
@@ -77,7 +77,7 @@
        "eslint-plugin-react-hooks": "^4.6.2",
        "husky": "^9.1.6",
        "jsdom": "^25.0.1",
-        "lint-staged": "^15.2.11",
+        "lint-staged": "^15.3.0",
        "msw": "^2.6.6",
        "postcss": "^8.4.47",
        "prettier": "^3.4.2",
@@ -1595,17 +1595,17 @@
      }
    },
    "node_modules/@monaco-editor/react": {
-      "version": "4.6.0",
-      "resolved": "https://registry.npmjs.org/@monaco-editor/react/-/react-4.6.0.tgz",
-      "integrity": "sha512-RFkU9/i7cN2bsq/iTkurMWOEErmYcY6JiQI3Jn+WeR/FGISH8JbHERjpS9oRuSOPvDMJI0Z8nJeKkbOs9sBYQw==",
+      "version": "4.7.0-rc.0",
+      "resolved": "https://registry.npmjs.org/@monaco-editor/react/-/react-4.7.0-rc.0.tgz",
+      "integrity": "sha512-YfjXkDK0bcwS0zo8PXptvQdCQfOPPtzGsAzmIv7PnoUGFdIohsR+NVDyjbajMddF+3cWUm/3q9NzP/DUke9a+w==",
      "license": "MIT",
      "dependencies": {
        "@monaco-editor/loader": "^1.4.0"
      },
      "peerDependencies": {
        "monaco-editor": ">= 0.25.0 < 1",
-        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
-        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
+        "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0",
+        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0"
      }
    },
    "node_modules/@mswjs/interceptors": {
@@ -2241,6 +2241,23 @@
        "react-dom": ">=18 || >=19.0.0-rc.0"
      }
    },
+    "node_modules/@nextui-org/listbox/node_modules/@tanstack/react-virtual": {
+      "version": "3.10.9",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.10.9.tgz",
+      "integrity": "sha512-OXO2uBjFqA4Ibr2O3y0YMnkrRWGVNqcvHQXmGvMu6IK8chZl3PrDxFXdGZ2iZkSrKh3/qUYoFqYe+Rx23RoU0g==",
+      "license": "MIT",
+      "dependencies": {
+        "@tanstack/virtual-core": "3.10.9"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/tannerlinsley"
+      },
+      "peerDependencies": {
+        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
+        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
+      }
+    },
    "node_modules/@nextui-org/menu": {
      "version": "2.2.8",
      "resolved": "https://registry.npmjs.org/@nextui-org/menu/-/menu-2.2.8.tgz",
@@ -2579,6 +2596,23 @@
        "react-dom": ">=18 || >=19.0.0-rc.0"
      }
    },
+    "node_modules/@nextui-org/select/node_modules/@tanstack/react-virtual": {
+      "version": "3.10.9",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.10.9.tgz",
+      "integrity": "sha512-OXO2uBjFqA4Ibr2O3y0YMnkrRWGVNqcvHQXmGvMu6IK8chZl3PrDxFXdGZ2iZkSrKh3/qUYoFqYe+Rx23RoU0g==",
+      "license": "MIT",
+      "dependencies": {
+        "@tanstack/virtual-core": "3.10.9"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/tannerlinsley"
+      },
+      "peerDependencies": {
+        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
+        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
+      }
+    },
    "node_modules/@nextui-org/shared-icons": {
      "version": "2.1.1",
      "resolved": "https://registry.npmjs.org/@nextui-org/shared-icons/-/shared-icons-2.1.1.tgz",
@@ -5321,10 +5355,9 @@
      }
    },
    "node_modules/@tanstack/react-query": {
-      "version": "5.62.10",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.62.10.tgz",
-      "integrity": "sha512-1e1WpHM5oGf27nWM/NWLY62/X9pbMBWa6ErWYmeuK0OqB9/g9UzA59ogiWbxCmS2wtAFQRhOdHhfSofrkhPl2g==",
-      "license": "MIT",
+      "version": "5.62.11",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.62.11.tgz",
+      "integrity": "sha512-Xb1nw0cYMdtFmwkvH9+y5yYFhXvLRCnXoqlzSw7UkqtCVFq3cG8q+rHZ2Yz1XrC+/ysUaTqbLKJqk95mCgC1oQ==",
      "dependencies": {
        "@tanstack/query-core": "5.62.9"
      },
@@ -5336,23 +5369,6 @@
        "react": "^18 || ^19"
      }
    },
-    "node_modules/@tanstack/react-virtual": {
-      "version": "3.10.9",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.10.9.tgz",
-      "integrity": "sha512-OXO2uBjFqA4Ibr2O3y0YMnkrRWGVNqcvHQXmGvMu6IK8chZl3PrDxFXdGZ2iZkSrKh3/qUYoFqYe+Rx23RoU0g==",
-      "license": "MIT",
-      "dependencies": {
-        "@tanstack/virtual-core": "3.10.9"
-      },
-      "funding": {
-        "type": "github",
-        "url": "https://github.com/sponsors/tannerlinsley"
-      },
-      "peerDependencies": {
-        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
-        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
-      }
-    },
    "node_modules/@tanstack/virtual-core": {
      "version": "3.10.9",
      "resolved": "https://registry.npmjs.org/@tanstack/virtual-core/-/virtual-core-3.10.9.tgz",
@@ -5603,30 +5619,23 @@
        "undici-types": "~6.20.0"
      }
    },
-    "node_modules/@types/prop-types": {
-      "version": "15.7.14",
-      "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.14.tgz",
-      "integrity": "sha512-gNMvNH49DJ7OJYv+KAKn0Xp45p8PLl6zo2YnvDIbTd4J6MER2BmWN49TG7n9LvkyihINxeKW8+3bfS2yDC9dzQ==",
-      "license": "MIT"
-    },
    "node_modules/@types/react": {
-      "version": "18.3.18",
-      "resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.18.tgz",
-      "integrity": "sha512-t4yC+vtgnkYjNSKlFx1jkAhH8LgTo2N/7Qvi83kdEaUtMDiwpbLAktKDaAMlRcJ5eSxZkH74eEGt1ky31d7kfQ==",
+      "version": "19.0.2",
+      "resolved": "https://registry.npmjs.org/@types/react/-/react-19.0.2.tgz",
+      "integrity": "sha512-USU8ZI/xyKJwFTpjSVIrSeHBVAGagkHQKPNbxeWwql/vDmnTIBgx+TJnhFnj1NXgz8XfprU0egV2dROLGpsBEg==",
      "license": "MIT",
      "dependencies": {
-        "@types/prop-types": "*",
        "csstype": "^3.0.2"
      }
    },
    "node_modules/@types/react-dom": {
-      "version": "18.3.5",
-      "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.5.tgz",
-      "integrity": "sha512-P4t6saawp+b/dFrUr2cvkVsfvPguwsxtH6dNIYRllMsefqFzkZk5UIjzyDOv5g1dXIPdG4Sp1yCR4Z6RCUsG/Q==",
+      "version": "19.0.2",
+      "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-19.0.2.tgz",
+      "integrity": "sha512-c1s+7TKFaDRRxr1TxccIX2u7sfCnc3RxkVyBIUA2lCpyqCF+QoAwQ/CBg7bsMdVwP120HEH143VQezKtef5nCg==",
      "dev": true,
      "license": "MIT",
      "peerDependencies": {
-        "@types/react": "^18.0.0"
+        "@types/react": "^19.0.0"
      }
    },
    "node_modules/@types/react-highlight": {
@@ -11179,13 +11188,12 @@
      "license": "MIT"
    },
    "node_modules/lint-staged": {
-      "version": "15.2.11",
-      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-15.2.11.tgz",
-      "integrity": "sha512-Ev6ivCTYRTGs9ychvpVw35m/bcNDuBN+mnTeObCL5h+boS5WzBEC6LHI4I9F/++sZm1m+J2LEiy0gxL/R9TBqQ==",
+      "version": "15.3.0",
+      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-15.3.0.tgz",
+      "integrity": "sha512-vHFahytLoF2enJklgtOtCtIjZrKD/LoxlaUusd5nh7dWv/dkKQJY74ndFSzxCdv7g0ueGg1ORgTSt4Y9LPZn9A==",
      "dev": true,
-      "license": "MIT",
      "dependencies": {
-        "chalk": "~5.3.0",
+        "chalk": "~5.4.1",
        "commander": "~12.1.0",
        "debug": "~4.4.0",
        "execa": "~8.0.1",
@@ -11207,11 +11215,10 @@
      }
    },
    "node_modules/lint-staged/node_modules/chalk": {
-      "version": "5.3.0",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-5.3.0.tgz",
-      "integrity": "sha512-dLitG79d+GV1Nb/VYcCDFivJeK1hiukt9QjRNVOsUtTy1rR1YJsmpGGTZ3qJos+uw7WmWF4wUwBd9jxjocFC2w==",
+      "version": "5.4.1",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-5.4.1.tgz",
+      "integrity": "sha512-zgVZuo2WcZgfUEmsn6eO3kINexW8RAE4maiQ8QNs8CtpPCSyMiYsULR3HQYkm3w8FIA3SberyMJMSldGsW+U3w==",
      "dev": true,
-      "license": "MIT",
      "engines": {
        "node": "^12.17.0 || ^14.13 || >=16.0.0"
      },
@@ -11544,6 +11551,7 @@
      "version": "1.4.0",
      "resolved": "https://registry.npmjs.org/loose-envify/-/loose-envify-1.4.0.tgz",
      "integrity": "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q==",
+      "dev": true,
      "license": "MIT",
      "dependencies": {
        "js-tokens": "^3.0.0 || ^4.0.0"
@@ -13763,10 +13771,9 @@
      "license": "MIT"
    },
    "node_modules/posthog-js": {
-      "version": "1.203.1",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.203.1.tgz",
-      "integrity": "sha512-r/WiSyz6VNbIKEV/30+aD5gdrYkFtmZwvqNa6h9frl8hG638v098FrXaq3EYzMcCdkQf3phaZTDIAFKegpiTjw==",
-      "license": "MIT",
+      "version": "1.203.2",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.203.2.tgz",
+      "integrity": "sha512-3aLpEhM4i9sQQtobRmDttJ3rTW1+gwQ9HL7QiOeDueE2T7CguYibYS7weY1UhXMerx5lh1A7+szlOJTTibifLQ==",
      "dependencies": {
        "core-js": "^3.38.1",
        "fflate": "^0.4.8",
@@ -14067,28 +14074,24 @@
      }
    },
    "node_modules/react": {
-      "version": "18.3.1",
-      "resolved": "https://registry.npmjs.org/react/-/react-18.3.1.tgz",
-      "integrity": "sha512-wS+hAgJShR0KhEvPJArfuPVN1+Hz1t0Y6n5jLrGQbkb4urgPE/0Rve+1kMB1v/oWgHgm4WIcV+i7F2pTVj+2iQ==",
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react/-/react-19.0.0.tgz",
+      "integrity": "sha512-V8AVnmPIICiWpGfm6GLzCR/W5FXLchHop40W4nXBmdlEceh16rCN8O8LNWm5bh5XUX91fh7KpA+W0TgMKmgTpQ==",
      "license": "MIT",
-      "dependencies": {
-        "loose-envify": "^1.1.0"
-      },
      "engines": {
        "node": ">=0.10.0"
      }
    },
    "node_modules/react-dom": {
-      "version": "18.3.1",
-      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-18.3.1.tgz",
-      "integrity": "sha512-5m4nQKp+rZRb09LNH59GM4BxTh9251/ylbKIbpe7TpGxfJ+9kv6BLkLBXIjjspbgbnIBNqlI23tRnTWT0snUIw==",
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.0.0.tgz",
+      "integrity": "sha512-4GV5sHFG0e/0AD4X+ySy6UJd3jVl1iNsNHdpad0qhABJ11twS3TTBnseqsKurKcsNqCEFeGL3uLpVChpIO3QfQ==",
      "license": "MIT",
      "dependencies": {
-        "loose-envify": "^1.1.0",
-        "scheduler": "^0.23.2"
+        "scheduler": "^0.25.0"
      },
      "peerDependencies": {
-        "react": "^18.3.1"
+        "react": "^19.0.0"
      }
    },
    "node_modules/react-highlight": {
@@ -14117,10 +14120,9 @@
      }
    },
    "node_modules/react-i18next": {
-      "version": "15.2.0",
-      "resolved": "https://registry.npmjs.org/react-i18next/-/react-i18next-15.2.0.tgz",
-      "integrity": "sha512-iJNc8111EaDtVTVMKigvBtPHyrJV+KblWG73cUxqp+WmJCcwkzhWNFXmkAD5pwP2Z4woeDj/oXDdbjDsb3Gutg==",
-      "license": "MIT",
+      "version": "15.4.0",
+      "resolved": "https://registry.npmjs.org/react-i18next/-/react-i18next-15.4.0.tgz",
+      "integrity": "sha512-Py6UkX3zV08RTvL6ZANRoBh9sL/ne6rQq79XlkHEdd82cZr2H9usbWpUNVadJntIZP2pu3M2rL1CN+5rQYfYFw==",
      "dependencies": {
        "@babel/runtime": "^7.25.0",
        "html-parse-stringify": "^3.0.1"
@@ -14926,13 +14928,10 @@
      }
    },
    "node_modules/scheduler": {
-      "version": "0.23.2",
-      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.23.2.tgz",
-      "integrity": "sha512-UOShsPwz7NrMUqhR6t0hWjFduvOzbtv7toDH1/hIrfRNIDBnnBWd0CwJTGvTpngVlmwGCdP9/Zl/tVrDqcuYzQ==",
-      "license": "MIT",
-      "dependencies": {
-        "loose-envify": "^1.1.0"
-      }
+      "version": "0.25.0",
+      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.25.0.tgz",
+      "integrity": "sha512-xFVuu11jh+xcO7JOAGJNOXld8/TcEHK/4CituBUeUb5hqxJLj9YuemAEuvm9gQ/+pgXYfbQuqAkiYu+u7YEsNA==",
+      "license": "MIT"
    },
    "node_modules/scroll-into-view-if-needed": {
      "version": "3.0.10",
@@ -7,13 +7,13 @@
    "node": ">=20.0.0"
  },
  "dependencies": {
-    "@monaco-editor/react": "^4.6.0",
+    "@monaco-editor/react": "^4.7.0-rc.0",
    "@nextui-org/react": "^2.6.10",
    "@react-router/node": "^7.1.1",
    "@react-router/serve": "^7.1.1",
    "@react-types/shared": "^3.25.0",
    "@reduxjs/toolkit": "^2.5.0",
-    "@tanstack/react-query": "^5.62.10",
+    "@tanstack/react-query": "^5.62.11",
    "@vitejs/plugin-react": "^4.3.2",
    "@xterm/addon-fit": "^0.10.0",
    "@xterm/xterm": "^5.4.0",
@@ -26,12 +26,12 @@
    "isbot": "^5.1.19",
    "jose": "^5.9.4",
    "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.203.1",
-    "react": "^18.3.1",
-    "react-dom": "^18.3.1",
+    "posthog-js": "^1.203.2",
+    "react": "^19.0.0",
+    "react-dom": "^19.0.0",
    "react-highlight": "^0.15.0",
    "react-hot-toast": "^2.4.1",
-    "react-i18next": "^15.2.0",
+    "react-i18next": "^15.4.0",
    "react-icons": "^5.4.0",
    "react-markdown": "^9.0.1",
    "react-redux": "^9.2.0",
@@ -42,7 +42,7 @@
    "sirv-cli": "^3.0.0",
    "socket.io-client": "^4.8.1",
    "tailwind-merge": "^2.6.0",
-    "vite": "^5.4.9",
+    "vite": "^5.4.11",
    "web-vitals": "^3.5.2",
    "ws": "^8.18.0"
  },
@@ -83,8 +83,8 @@
    "@testing-library/react": "^16.1.0",
    "@testing-library/user-event": "^14.5.2",
    "@types/node": "^22.10.2",
-    "@types/react": "^18.3.11",
-    "@types/react-dom": "^18.3.0",
+    "@types/react": "^19.0.2",
+    "@types/react-dom": "^19.0.2",
    "@types/react-highlight": "^0.12.8",
    "@types/react-syntax-highlighter": "^15.5.13",
    "@types/ws": "^8.5.12",
@@ -104,7 +104,7 @@
    "eslint-plugin-react-hooks": "^4.6.2",
    "husky": "^9.1.6",
    "jsdom": "^25.0.1",
-    "lint-staged": "^15.2.11",
+    "lint-staged": "^15.3.0",
    "msw": "^2.6.6",
    "postcss": "^8.4.47",
    "prettier": "^3.4.2",
@@ -8,8 +8,8 @@
 * - Please do NOT serve this file on production.
 */

-const PACKAGE_VERSION = '2.6.6'
-const INTEGRITY_CHECKSUM = 'ca7800994cc8bfb5eb961e037c877074'
+const PACKAGE_VERSION = '2.7.0'
+const INTEGRITY_CHECKSUM = '00729d72e3b82faf54ca8b9621dbb96f'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()

@@ -199,7 +199,19 @@ async function getResponse(event, client, requestId) {
    // Remove the "accept" header value that marked this request as passthrough.
    // This prevents request alteration and also keeps it compliant with the
    // user-defined CORS policies.
-    headers.delete('accept', 'msw/passthrough')
+    const acceptHeader = headers.get('accept')
+    if (acceptHeader) {
+      const values = acceptHeader.split(',').map((value) => value.trim())
+      const filteredValues = values.filter(
+        (value) => value !== 'msw/passthrough',
+      )
+
+      if (filteredValues.length > 0) {
+        headers.set('accept', filteredValues.join(', '))
+      } else {
+        headers.delete('accept')
+      }
+    }

    return fetch(requestClone, { headers })
  }
@@ -106,15 +106,28 @@ export const retrieveGitHubUser = async () => {

 export const retrieveLatestGitHubCommit = async (
  repository: string,
-): Promise<GitHubCommit> => {
-  const response = await github.get<GitHubCommit[]>(
-    `/repos/${repository}/commits`,
-    {
-      params: {
-        per_page: 1,
+): Promise<GitHubCommit | null> => {
+  try {
+    const response = await github.get<GitHubCommit[]>(
+      `/repos/${repository}/commits`,
+      {
+        params: {
+          per_page: 1,
+        },
      },
-    },
-  );
-
-  return response.data[0];
+    );
+    return response.data[0] || null;
+  } catch (error) {
+    if (!error || typeof error !== "object") {
+      throw new Error("Unknown error occurred");
+    }
+    const axiosError = error as { response?: { status: number } };
+    if (axiosError.response?.status === 409) {
+      // Repository is empty, no commits yet
+      return null;
+    }
+    throw new Error(
+      error instanceof Error ? error.message : "Unknown error occurred",
+    );
+  }
 };
@@ -250,14 +250,12 @@ class OpenHands {

  static async newConversation(params: {
    githubToken?: string;
-    args?: Record<string, unknown>;
    selectedRepository?: string;
  }): Promise<{ conversation_id: string }> {
    const { data } = await openHands.post<{
      conversation_id: string;
    }>("/api/conversations", {
      github_token: params.githubToken,
-      args: params.args,
      selected_repository: params.selectedRepository,
    });
    // TODO: remove this once we have a multi-conversation UI
@@ -1,6 +1,6 @@
 import React from "react";

-function ArrowIcon(): JSX.Element {
+function ArrowIcon() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -1,6 +1,6 @@
 import React from "react";

-function CogTooth(): JSX.Element {
+function CogTooth() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -1,6 +1,6 @@
 import React from "react";

-function ConfirmIcon(): JSX.Element {
+function ConfirmIcon() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -1,6 +1,6 @@
 import React from "react";

-function PauseIcon(): JSX.Element {
+function PauseIcon() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -1,6 +1,6 @@
 import React from "react";

-function PlayIcon(): JSX.Element {
+function PlayIcon() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -1,6 +1,6 @@
 import React from "react";

-function RejectIcon(): JSX.Element {
+function RejectIcon() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -1,6 +1,6 @@
 import React from "react";

-function StopIcon(): JSX.Element {
+function StopIcon() {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
@@ -8,7 +8,7 @@ import {
  FaPython,
 } from "react-icons/fa";

-export const EXTENSION_ICON_MAP: Record<string, JSX.Element> = {
+export const EXTENSION_ICON_MAP: Record<string, React.ReactNode> = {
  js: <DiJavascript />,
  ts: <DiJavascript />,
  py: <FaPython />,
@@ -1,7 +1,9 @@
+import { useTranslation } from "react-i18next";
 import { ContextMenu } from "./context-menu";
 import { ContextMenuListItem } from "./context-menu-list-item";
 import { ContextMenuSeparator } from "./context-menu-separator";
 import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
+import { I18nKey } from "#/i18n/declaration";

 interface AccountSettingsContextMenuProps {
  onClickAccountSettings: () => void;
@@ -17,6 +19,7 @@ export function AccountSettingsContextMenu({
  isLoggedIn,
 }: AccountSettingsContextMenuProps) {
  const ref = useClickOutsideElement<HTMLUListElement>(onClose);
+  const { t } = useTranslation();

  return (
    <ContextMenu
@@ -25,11 +28,11 @@ export function AccountSettingsContextMenu({
      className="absolute left-full -top-1 z-10"
    >
      <ContextMenuListItem onClick={onClickAccountSettings}>
-        Account Settings
+        {t(I18nKey.ACCOUNT_SETTINGS$SETTINGS)}
      </ContextMenuListItem>
      <ContextMenuSeparator />
      <ContextMenuListItem onClick={onLogout} isDisabled={!isLoggedIn}>
-        Logout
+        {t(I18nKey.ACCOUNT_SETTINGS$LOGOUT)}
      </ContextMenuListItem>
    </ContextMenu>
  );
@@ -2,13 +2,19 @@ import React from "react";
 import { cn } from "#/utils/utils";

 interface ContextMenuProps {
+  ref: React.RefObject<HTMLUListElement | null>;
  testId?: string;
  children: React.ReactNode;
  className?: React.HTMLAttributes<HTMLUListElement>["className"];
 }

-export const ContextMenu = React.forwardRef<HTMLUListElement, ContextMenuProps>(
-  ({ testId, children, className }, ref) => (
+export function ContextMenu({
+  testId,
+  children,
+  className,
+  ref,
+}: ContextMenuProps) {
+  return (
    <ul
      data-testid={testId}
      ref={ref}
@@ -16,7 +22,5 @@ export const ContextMenu = React.forwardRef<HTMLUListElement, ContextMenuProps>(
    >
      {children}
    </ul>
-  ),
-);
-
-ContextMenu.displayName = "ContextMenu";
+  );
+}
@@ -4,7 +4,7 @@ interface FolderIconProps {
  isOpen: boolean;
 }

-export function FolderIcon({ isOpen }: FolderIconProps): JSX.Element {
+export function FolderIcon({ isOpen }: FolderIconProps) {
  return isOpen ? (
    <FaFolderOpen color="D9D3D0" className="icon" />
  ) : (
@@ -1,5 +1,6 @@
 import React from "react";
 import posthog from "posthog-js";
+import { useTranslation } from "react-i18next";
 import EllipsisH from "#/icons/ellipsis-h.svg?react";
 import { ProjectMenuCardContextMenu } from "./project.menu-card-context-menu";
 import { ProjectMenuDetailsPlaceholder } from "./project-menu-details-placeholder";
@@ -7,6 +8,7 @@ import { ProjectMenuDetails } from "./project-menu-details";
 import { ConnectToGitHubModal } from "#/components/shared/modals/connect-to-github-modal";
 import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
 import { DownloadModal } from "#/components/shared/download-modal";
+import { I18nKey } from "#/i18n/declaration";

 interface ProjectMenuCardProps {
  isConnectedToGitHub: boolean;
@@ -21,6 +23,8 @@ export function ProjectMenuCard({
  isConnectedToGitHub,
  githubData,
 }: ProjectMenuCardProps) {
+  const { t } = useTranslation();
+
  const [contextMenuIsOpen, setContextMenuIsOpen] = React.useState(false);
  const [connectToGitHubModalOpen, setConnectToGitHubModalOpen] =
    React.useState(false);
@@ -71,7 +75,7 @@ export function ProjectMenuCard({
        <button
          type="button"
          onClick={toggleMenuVisibility}
-          aria-label="Open project menu"
+          aria-label={t(I18nKey.PROJECT_MENU_CARD$OPEN)}
        >
          <EllipsisH width={36} height={36} />
        </button>
@@ -30,7 +30,9 @@ export function ProjectMenuDetailsPlaceholder({
            "hover:underline hover:underline-offset-2",
          )}
        >
-          {!isConnectedToGitHub ? "Connect to GitHub" : "Connected"}
+          {!isConnectedToGitHub
+            ? t(I18nKey.PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECT_TO_GITHUB)
+            : t(I18nKey.PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECTED)}
          <CloudConnection width={12} height={12} />
        </span>
      </button>
@@ -3,7 +3,6 @@ import { useLocation } from "react-router";
 import { useAuth } from "#/context/auth-context";
 import { useSettings } from "#/context/settings-context";
 import { useGitHubUser } from "#/hooks/query/use-github-user";
-import { useIsAuthed } from "#/hooks/query/use-is-authed";
 import { UserActions } from "./user-actions";
 import { AllHandsLogoButton } from "#/components/shared/buttons/all-hands-logo-button";
 import { DocsButton } from "#/components/shared/buttons/docs-button";
@@ -18,13 +17,12 @@ export function Sidebar() {
  const location = useLocation();

  const user = useGitHubUser();
-  const { data: isAuthed } = useIsAuthed();
-
  const { logout } = useAuth();
-  const { settingsAreUpToDate } = useSettings();
+  const { settingsAreUpToDate, settings } = useSettings();

  const [accountSettingsModalOpen, setAccountSettingsModalOpen] =
    React.useState(false);
+
  const [settingsModalIsOpen, setSettingsModalIsOpen] = React.useState(false);
  const [startNewProjectModalIsOpen, setStartNewProjectModalIsOpen] =
    React.useState(false);
@@ -36,6 +34,12 @@ export function Sidebar() {
    }
  }, [user.isError]);

+  React.useEffect(() => {
+    if (!settings || !settingsAreUpToDate) {
+      setSettingsModalIsOpen(true);
+    }
+  }, [settings, settingsAreUpToDate]);
+
  const handleAccountSettingsModalClose = () => {
    // If the user closes the modal without connecting to GitHub,
    // we need to log them out to clear the invalid token from the
@@ -49,9 +53,6 @@ export function Sidebar() {
      setStartNewProjectModalIsOpen(true);
  };

-  const showSettingsModal =
-    isAuthed && (!settingsAreUpToDate || settingsModalIsOpen);
-
  return (
    <>
      <aside className="h-[40px] md:h-auto px-1 flex flex-row md:flex-col gap-1">
@@ -79,7 +80,7 @@ export function Sidebar() {
      {accountSettingsModalOpen && (
        <AccountSettingsModal onClose={handleAccountSettingsModalClose} />
      )}
-      {showSettingsModal && (
+      {!accountSettingsModalOpen && settingsModalIsOpen && (
        <SettingsModal onClose={() => setSettingsModalIsOpen(false)} />
      )}
      {startNewProjectModalIsOpen && (
@@ -1,3 +1,4 @@
+import { Tooltip } from "@nextui-org/react";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import DefaultUserAvatar from "#/icons/default-user.svg?react";
 import { cn } from "#/utils/utils";
@@ -10,7 +11,7 @@ interface UserAvatarProps {
 }

 export function UserAvatar({ onClick, avatarUrl, isLoading }: UserAvatarProps) {
-  return (
+  const buttonContent = (
    <button
      data-testid="user-avatar"
      type="button"
@@ -31,4 +32,10 @@ export function UserAvatar({ onClick, avatarUrl, isLoading }: UserAvatarProps) {
      {isLoading && <LoadingSpinner size="small" />}
    </button>
  );
+
+  return (
+    <Tooltip content="Account settings" closeDelay={100}>
+      {buttonContent}
+    </Tooltip>
+  );
 }
@@ -1,4 +1,5 @@
 import AllHandsLogo from "#/assets/branding/all-hands-logo.svg?react";
+import { TooltipButton } from "./tooltip-button";

 interface AllHandsLogoButtonProps {
  onClick: () => void;
@@ -6,8 +7,12 @@ interface AllHandsLogoButtonProps {

 export function AllHandsLogoButton({ onClick }: AllHandsLogoButtonProps) {
  return (
-    <button type="button" aria-label="All Hands Logo" onClick={onClick}>
+    <TooltipButton
+      tooltip="All Hands AI"
+      ariaLabel="All Hands Logo"
+      onClick={onClick}
+    >
      <AllHandsLogo width={34} height={23} />
-    </button>
+    </TooltipButton>
  );
 }
@@ -1,15 +1,14 @@
 import DocsIcon from "#/icons/docs.svg?react";
+import { TooltipButton } from "./tooltip-button";

 export function DocsButton() {
  return (
-    <a
+    <TooltipButton
+      tooltip="Documentation"
+      ariaLabel="Documentation"
      href="https://docs.all-hands.dev"
-      aria-label="Documentation"
-      target="_blank"
-      rel="noreferrer noopener"
-      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
    >
      <DocsIcon width={28} height={28} />
-    </a>
+    </TooltipButton>
  );
 }
@@ -1,4 +1,5 @@
 import NewProjectIcon from "#/icons/new-project.svg?react";
+import { TooltipButton } from "./tooltip-button";

 interface ExitProjectButtonProps {
  onClick: () => void;
@@ -6,13 +7,13 @@ interface ExitProjectButtonProps {

 export function ExitProjectButton({ onClick }: ExitProjectButtonProps) {
  return (
-    <button
-      data-testid="new-project-button"
-      type="button"
-      aria-label="Start new project"
+    <TooltipButton
+      tooltip="Start new project"
+      ariaLabel="Start new project"
      onClick={onClick}
+      testId="new-project-button"
    >
      <NewProjectIcon width={28} height={28} />
-    </button>
+    </TooltipButton>
  );
 }
@@ -1,4 +1,5 @@
 import CogTooth from "#/assets/cog-tooth";
+import { TooltipButton } from "./tooltip-button";

 interface SettingsButtonProps {
  onClick: () => void;
@@ -6,13 +7,8 @@ interface SettingsButtonProps {

 export function SettingsButton({ onClick }: SettingsButtonProps) {
  return (
-    <button
-      type="button"
-      aria-label="Settings"
-      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
-      onClick={onClick}
-    >
+    <TooltipButton tooltip="Settings" ariaLabel="Settings" onClick={onClick}>
      <CogTooth />
-    </button>
+    </TooltipButton>
  );
 }
@@ -0,0 +1,52 @@
+import { Tooltip } from "@nextui-org/react";
+import { ReactNode } from "react";
+
+interface TooltipButtonProps {
+  children: ReactNode;
+  tooltip: string;
+  onClick?: () => void;
+  href?: string;
+  ariaLabel: string;
+  testId?: string;
+}
+
+export function TooltipButton({
+  children,
+  tooltip,
+  onClick,
+  href,
+  ariaLabel,
+  testId,
+}: TooltipButtonProps) {
+  const buttonContent = (
+    <button
+      type="button"
+      aria-label={ariaLabel}
+      data-testid={testId}
+      onClick={onClick}
+      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
+    >
+      {children}
+    </button>
+  );
+
+  const content = href ? (
+    <a
+      href={href}
+      target="_blank"
+      rel="noreferrer noopener"
+      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
+      aria-label={ariaLabel}
+    >
+      {children}
+    </a>
+  ) : (
+    buttonContent
+  );
+
+  return (
+    <Tooltip content={tooltip} closeDelay={100}>
+      {content}
+    </Tooltip>
+  );
+}
@@ -1,4 +1,6 @@
 import toast, { Toast } from "react-hot-toast";
+import { useTranslation } from "react-i18next";
+import { I18nKey } from "#/i18n/declaration";

 interface ErrorToastProps {
  id: Toast["id"];
@@ -6,6 +8,8 @@ interface ErrorToastProps {
 }

 export function ErrorToast({ id, error }: ErrorToastProps) {
+  const { t } = useTranslation();
+
  return (
    <div className="flex items-center justify-between w-full h-full">
      <span>{error}</span>
@@ -14,7 +18,7 @@ export function ErrorToast({ id, error }: ErrorToastProps) {
        onClick={() => toast.dismiss(id)}
        className="bg-neutral-500 px-1 rounded h-full"
      >
-        Close
+        {t(I18nKey.ERROR_TOAST$CLOSE_BUTTON_LABEL)}
      </button>
    </div>
  );
@@ -4,7 +4,7 @@ interface InvariantLogoIconProps {
  className?: string;
 }

-function InvariantLogoIcon({ className }: InvariantLogoIconProps): JSX.Element {
+function InvariantLogoIcon({ className }: InvariantLogoIconProps) {
  return (
    <svg
      width="39"
@@ -24,7 +24,7 @@ import { useGetTraces } from "#/hooks/query/use-get-traces";

 type SectionType = "logs" | "policy" | "settings";

-function SecurityInvariant(): JSX.Element {
+function SecurityInvariant() {
  const { t } = useTranslation();
  const { logs } = useSelector((state: RootState) => state.securityAnalyzer);

@@ -122,7 +122,7 @@ function SecurityInvariant(): JSX.Element {
    [],
  );

-  const sections: { [key in SectionType]: JSX.Element } = {
+  const sections: Record<SectionType, React.ReactNode> = {
    logs: (
      <>
        <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
@@ -86,13 +86,13 @@ export function SettingsForm({
    }
  };

-  const handleFormSubmission = (formData: FormData) => {
+  const handleFormSubmission = async (formData: FormData) => {
    const keys = Array.from(formData.keys());
    const isUsingAdvancedOptions = keys.includes("use-advanced-options");
    const newSettings = extractSettings(formData);

    saveSettingsView(isUsingAdvancedOptions ? "advanced" : "basic");
-    saveSettings(newSettings);
+    await saveSettings(newSettings);
    resetOngoingSession();

    posthog.capture("settings_saved", {
@@ -101,8 +101,8 @@ export function SettingsForm({
    });
  };

-  const handleConfirmResetSettings = () => {
-    saveSettings(getDefaultSettings());
+  const handleConfirmResetSettings = async () => {
+    await saveSettings(getDefaultSettings());
    resetOngoingSession();
    posthog.capture("settings_reset");

@@ -11,7 +11,6 @@ import {
 } from "#/state/initial-query-slice";
 import OpenHands from "#/api/open-hands";
 import { useAuth } from "#/context/auth-context";
-import { useSettings } from "#/context/settings-context";

 import { SuggestionBubble } from "#/components/features/suggestions/suggestion-bubble";
 import { SUGGESTIONS } from "#/utils/suggestions";
@@ -24,12 +23,15 @@ import { ImageCarousel } from "../features/images/image-carousel";
 import { UploadImageInput } from "../features/images/upload-image-input";
 import { LoadingSpinner } from "./loading-spinner";

-export const TaskForm = React.forwardRef<HTMLFormElement>((_, ref) => {
+interface TaskFormProps {
+  ref: React.RefObject<HTMLFormElement | null>;
+}
+
+export function TaskForm({ ref }: TaskFormProps) {
  const dispatch = useDispatch();
  const navigation = useNavigation();
  const navigate = useNavigate();
  const { gitHubToken } = useAuth();
-  const { settings } = useSettings();

  const { selectedRepository, files } = useSelector(
    (state: RootState) => state.initialQuery,
@@ -46,7 +48,6 @@ export const TaskForm = React.forwardRef<HTMLFormElement>((_, ref) => {
      return OpenHands.newConversation({
        githubToken: gitHubToken || undefined,
        selectedRepository: selectedRepository || undefined,
-        args: settings || undefined,
      });
    },
    onSuccess: ({ conversation_id: conversationId }, { q }) => {
@@ -89,7 +90,9 @@ export const TaskForm = React.forwardRef<HTMLFormElement>((_, ref) => {
    const formData = new FormData(event.currentTarget);

    const q = formData.get("q")?.toString();
-    newConversationMutation.mutate({ q });
+    if (q?.trim()) {
+      newConversationMutation.mutate({ q });
+    }
  };

  return (
@@ -161,6 +164,4 @@ export const TaskForm = React.forwardRef<HTMLFormElement>((_, ref) => {
      )}
    </div>
  );
-});
-
-TaskForm.displayName = "TaskForm";
+}
@@ -102,7 +102,7 @@ function AuthProvider({ children }: React.PropsWithChildren) {
    [gitHubTokenState],
  );

-  return <AuthContext.Provider value={value}>{children}</AuthContext.Provider>;
+  return <AuthContext value={value}>{children}</AuthContext>;
 }

 function useAuth() {
@@ -24,11 +24,7 @@ export function ConversationProvider({

  const value = useMemo(() => ({ conversationId }), [conversationId]);

-  return (
-    <ConversationContext.Provider value={value}>
-      {children}
-    </ConversationContext.Provider>
-  );
+  return <ConversationContext value={value}>{children}</ConversationContext>;
 }

 export function useConversation() {
@@ -55,9 +55,7 @@ function FilesProvider({ children }: FilesProviderProps) {
    [paths, setPaths, files, setFileContent, selectedPath, setSelectedPath],
  );

-  return (
-    <FilesContext.Provider value={value}>{children}</FilesContext.Provider>
-  );
+  return <FilesContext value={value}>{children}</FilesContext>;
 }

 function useFiles() {
@@ -4,7 +4,7 @@ import { useQuery, useQueryClient } from "@tanstack/react-query";
 import {
  getSettings,
  Settings,
-  saveSettings as updateAndSaveSettingsToLocalStorage,
+  saveSettings,
  settingsAreUpToDate as checkIfSettingsAreUpToDate,
  DEFAULT_SETTINGS,
 } from "#/services/settings";
@@ -33,8 +33,8 @@ function SettingsProvider({ children }: React.PropsWithChildren) {
  );
  const queryClient = useQueryClient();

-  const saveSettings = (newSettings: Partial<Settings>) => {
-    updateAndSaveSettingsToLocalStorage(newSettings);
+  const handleSaveSettings = async (newSettings: Partial<Settings>) => {
+    await saveSettings(newSettings);
    queryClient.invalidateQueries({ queryKey: SETTINGS_QUERY_KEY });
    setSettingsAreUpToDate(checkIfSettingsAreUpToDate());
  };
@@ -49,16 +49,12 @@ function SettingsProvider({ children }: React.PropsWithChildren) {
    () => ({
      settings,
      settingsAreUpToDate,
-      saveSettings,
+      saveSettings: handleSaveSettings,
    }),
    [settings, settingsAreUpToDate],
  );

-  return (
-    <SettingsContext.Provider value={value}>
-      {children}
-    </SettingsContext.Provider>
-  );
+  return <SettingsContext value={value}>{children}</SettingsContext>;
 }

 function useSettings() {
@@ -151,11 +151,7 @@ export function WsClientProvider({
    [status, messageRateHandler.isUnderThreshold, events],
  );

-  return (
-    <WsClientContext.Provider value={value}>
-      {children}
-    </WsClientContext.Provider>
-  );
+  return <WsClientContext value={value}>{children}</WsClientContext>;
 }

 export function useWsClient() {
@@ -20,7 +20,7 @@ export function useDownloadProgress(
  const [progress, setProgress] =
    useState<DownloadProgressState>(INITIAL_PROGRESS);
  const progressRef = useRef<DownloadProgressState>(INITIAL_PROGRESS);
-  const abortController = useRef<AbortController>();
+  const abortController = useRef<AbortController>(null);
  const { conversationId } = useConversation();

  // Create AbortController on mount
@@ -31,7 +31,7 @@ export function useDownloadProgress(
    progressRef.current = INITIAL_PROGRESS;
    return () => {
      controller.abort();
-      abortController.current = undefined;
+      abortController.current = null;
    };
  }, []); // Empty deps array - only run on mount/unmount

@@ -1,6 +1,6 @@
 import { RefObject, useEffect, useState } from "react";

-export function useScrollToBottom(scrollRef: RefObject<HTMLDivElement>) {
+export function useScrollToBottom(scrollRef: RefObject<HTMLDivElement | null>) {
  // for auto-scroll

  const [autoScroll, setAutoScroll] = useState(true);
@@ -930,7 +930,7 @@
    "pt": "Configurações de compartilhamento",
    "tr": "Paylaşım ayarları"
  },
-  "SECURITY$UNKNOWN_ANALYZER_LABEL":{
+  "SECURITY$UNKNOWN_ANALYZER_LABEL": {
    "en": "Unknown security analyzer chosen",
    "es": "Analizador de seguridad desconocido",
    "zh-CN": "选择了未知的安全分析器",
@@ -1852,19 +1852,19 @@
    "fr": "En attente que le client soit prêt...",
    "tr": "İstemcinin hazır olması bekleniyor..."
  },
-  "ACCOUNT_SETTINGS_MODAL$DISCONNECT":{
+  "ACCOUNT_SETTINGS_MODAL$DISCONNECT": {
    "en": "Disconnect",
    "es": "Desconectar"
  },
-  "ACCOUNT_SETTINGS_MODAL$SAVE":{
+  "ACCOUNT_SETTINGS_MODAL$SAVE": {
    "en": "Save",
    "es": "Guardar"
  },
-  "ACCOUNT_SETTINGS_MODAL$CLOSE":{
+  "ACCOUNT_SETTINGS_MODAL$CLOSE": {
    "en": "Close",
    "es": "Cerrar"
  },
-  "ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID":{
+  "ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID": {
    "en": "GitHub token is invalid. Please try again.",
    "es": ""
  },
@@ -1973,12 +1973,18 @@
    "es": "Toda la información guardada en tu configuración de IA será eliminada, incluyendo tus API Keys"
  },
  "PROJECT_MENU_DETAILS_PLACEHOLDER$NEW_PROJECT_LABEL": {
-    "en":"New Project",
-    "es":"Nuevo proyecto"
+    "en": "New Project",
+    "es": "Nuevo proyecto"
+  },
+  "PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECT_TO_GITHUB": {
+    "en": "Connect to GitHub"
+  },
+  "PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECTED": {
+    "en": "Connected"
  },
  "PROJECT_MENU_DETAILS$AGO_LABEL": {
-    "en":"ago",
-    "es":"atrás"
+    "en": "ago",
+    "es": "atrás"
  },
  "STATUS$ERROR_LLM_AUTHENTICATION": {
    "en": "Error authenticating with the LLM provider. Please check your API key",
@@ -2005,6 +2011,39 @@
    "en": "Download files",
    "es": "Descargar archivos"
  },
+  "PROJECT_MENU_CARD$OPEN": {
+    "en": "Open project menu"
+  },
+  "ACTION_BUTTON$RESUME": {
+    "en": "Resume the agent task"
+  },
+  "ACTION_BUTTON$PAUSE": {
+    "en": "Pause the current task"
+  },
+  "BROWSER$SCREENSHOT_ALT": {
+    "en": "Browser Screenshot"
+  },
+  "ACCOUNT_SETTINGS$SETTINGS": {
+    "en": "Account Settings"
+  },
+  "ACCOUNT_SETTINGS$LOGOUT": {
+    "en": "Logout"
+  },
+  "ERROR_TOAST$CLOSE_BUTTON_LABEL": {
+    "en": "Close"
+  },
+  "FILE_EXPLORER$UPLOAD": {
+    "en": "Upload File"
+  },
+  "FILE_EXPLORER$REFRESH_WORKSPACE": {
+    "en": "Refresh workspace"
+  },
+  "FILE_EXPLORER$OPEN_WORKSPACE": {
+    "en": "Open workspace"
+  },
+  "FILE_EXPLORER$CLOSE_WORKSPACE": {
+    "en": "Close workspace"
+  },
  "ACTION_MESSAGE$RUN": {
    "en": "Running a bash command"
  },
@@ -36,15 +36,15 @@ function Home() {
  return (
    <div
      data-testid="root-index"
-      className="bg-root-secondary h-full rounded-xl flex flex-col items-center justify-center relative overflow-y-auto"
+      className="bg-root-secondary h-full rounded-xl flex flex-col items-center justify-center relative overflow-y-auto px-2"
    >
      <HeroHeading />
-      <div className="flex flex-col gap-8 w-[600px] items-center">
+      <div className="flex flex-col gap-8 w-full md:w-[600px] items-center">
        <div className="flex flex-col gap-2 w-full">
          <TaskForm ref={formRef} />
        </div>

-        <div className="flex gap-4 w-full">
+        <div className="flex gap-4 w-full flex-col md:flex-row">
          <GitHubRepositoriesSuggestionBox
            handleSubmit={() => formRef.current?.requestSubmit()}
            repositories={
@@ -77,14 +77,14 @@ function FileViewer() {
  return (
    <div className="flex h-full bg-neutral-900 relative">
      <FileExplorer isOpen={fileExplorerIsOpen} onToggle={toggleFileExplorer} />
-      <div className="w-full">
+      <div className="w-full h-full flex flex-col">
        {selectedPath && (
          <div className="flex w-full items-center justify-between self-end p-2">
            <span className="text-sm text-neutral-500">{selectedPath}</span>
          </div>
        )}
        {selectedPath && files[selectedPath] && (
-          <div className="p-4">
+          <div className="p-4 flex-1 overflow-auto">
            <SyntaxHighlighter
              language={getLanguageFromPath(selectedPath)}
              style={vscDarkPlus}
@@ -87,6 +87,7 @@ export const saveSettings = async (
    const { data } = await openHands.post("/api/settings", apiSettings);
    return data;
  } catch (error) {
+    // Error handled by returning false
    return false;
  }
 };
@@ -130,9 +131,9 @@ export const getDefaultSettings = (): Settings => DEFAULT_SETTINGS;
 * Get the settings from the server or use the default settings if not found
 */
 export const getSettings = async (): Promise<Settings> => {
-  const { data: apiSettings } =
-    await openHands.get<ApiSettings>("/api/settings");
-  if (apiSettings != null) {
+  try {
+    const { data: apiSettings } =
+      await openHands.get<ApiSettings>("/api/settings");
    return {
      LLM_MODEL: apiSettings.llm_model,
      LLM_BASE_URL: apiSettings.llm_base_url,
@@ -142,6 +143,14 @@ export const getSettings = async (): Promise<Settings> => {
      SECURITY_ANALYZER: apiSettings.security_analyzer,
      LLM_API_KEY: "",
    };
+  } catch (error) {
+    // @ts-expect-error we don't have a type annotation for the response
+    if (error.response?.status !== 404) {
+      throw error;
+    }
  }
-  return getLocalStorageSettings();
+  // FIXME: remove local storage settings after 1/31/2025
+  const localSettings = getLocalStorageSettings();
+  await saveSettings(localSettings);
+  return localSettings;
 };
@@ -148,9 +148,9 @@ export const chatSlice = createSlice({
      } else if (observationID === "run_ipython") {
        // For IPython, we consider it successful if there's no error message
        const ipythonObs = observation.payload as IPythonObservation;
-        causeMessage.success = !ipythonObs.message
+        causeMessage.success = !ipythonObs.content
          .toLowerCase()
-          .includes("error");
+          .includes("error:");
      }

      if (observationID === "run" || observationID === "run_ipython") {
@@ -1,17 +0,0 @@
-import toast from "react-hot-toast";
-import { ErrorToast } from "#/components/shared/error-toast";
-
-export const displayErrorToast = (error: string) =>
-  toast((t) => <ErrorToast id={t.id} error={error} />, {
-    style: {
-      background: "#C63143",
-      color: "#fff",
-      fontSize: "12px",
-      fontWeight: "500",
-      lineHeight: "20px",
-      borderRadius: "4px",
-      width: "336px",
-    },
-    duration: Infinity,
-    position: "bottom-right",
-  });
@@ -3,14 +3,12 @@
 import React, { PropsWithChildren } from "react";
 import { Provider } from "react-redux";
 import { configureStore } from "@reduxjs/toolkit";
-// eslint-disable-next-line import/no-extraneous-dependencies
 import { RenderOptions, render } from "@testing-library/react";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
-import { I18nextProvider } from "react-i18next";
+import { I18nextProvider, initReactI18next } from "react-i18next";
 import i18n from "i18next";
-import { initReactI18next } from "react-i18next";
-import { AppStore, RootState, rootReducer } from "./src/store";
 import { vi } from "vitest";
+import { AppStore, RootState, rootReducer } from "./src/store";
 import { AuthProvider } from "#/context/auth-context";
 import { SettingsProvider } from "#/context/settings-context";
 import { ConversationProvider } from "#/context/conversation-context";
@@ -26,22 +24,20 @@ vi.mock("react-router", async () => {
 });

 // Initialize i18n for tests
-i18n
-  .use(initReactI18next)
-  .init({
-    lng: "en",
-    fallbackLng: "en",
-    ns: ["translation"],
-    defaultNS: "translation",
-    resources: {
-      en: {
-        translation: {},
-      },
+i18n.use(initReactI18next).init({
+  lng: "en",
+  fallbackLng: "en",
+  ns: ["translation"],
+  defaultNS: "translation",
+  resources: {
+    en: {
+      translation: {},
    },
-    interpolation: {
-      escapeValue: false,
-    },
-  });
+  },
+  interpolation: {
+    escapeValue: false,
+  },
+});

 const setupStore = (preloadedState?: Partial<RootState>): AppStore =>
  configureStore({
@@ -67,16 +63,14 @@ export function renderWithProviders(
    ...renderOptions
  }: ExtendedRenderOptions = {},
 ) {
-  function Wrapper({ children }: PropsWithChildren<object>): JSX.Element {
+  function Wrapper({ children }: PropsWithChildren) {
    return (
      <Provider store={store}>
        <QueryClientProvider client={new QueryClient()}>
          <SettingsProvider>
            <AuthProvider>
              <ConversationProvider>
-                <I18nextProvider i18n={i18n}>
-                    {children}
-                </I18nextProvider>
+                <I18nextProvider i18n={i18n}>{children}</I18nextProvider>
              </ConversationProvider>
            </AuthProvider>
          </SettingsProvider>
@@ -83,6 +83,7 @@ class CodeActAgent(Agent):
        - llm (LLM): The llm to be used by this agent
        """
        super().__init__(llm, config)
+        self.pending_actions: deque[Action] = deque()
        self.reset()

        self.mock_function_calling = False
@@ -100,7 +101,7 @@ class CodeActAgent(Agent):
            codeact_enable_llm_editor=self.config.codeact_enable_llm_editor,
        )
        logger.debug(
-            f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2)}'
+            f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2, ensure_ascii=False).replace("\\n", "\n")}'
        )
        self.prompt_manager = PromptManager(
            microagent_dir=os.path.join(os.path.dirname(__file__), 'micro')
@@ -110,8 +111,6 @@ class CodeActAgent(Agent):
            disabled_microagents=self.config.disabled_microagents,
        )

-        self.pending_actions: deque[Action] = deque()
-
    def get_action_message(
        self,
        action: Action,
@@ -340,6 +339,7 @@ class CodeActAgent(Agent):
    def reset(self) -> None:
        """Resets the CodeAct Agent."""
        super().reset()
+        self.pending_actions.clear()

    def step(self, state: State) -> Action:
        """Performs one step using the CodeAct Agent.
@@ -270,9 +270,9 @@ StrReplaceEditorTool = ChatCompletionToolParam(
 )


-_WEB_DESCRIPTION = """Read (convert to markdown) content from a webpage. You should prefer using the `webpage_read` tool over the `browser` tool, but do use the `browser` tool if you need to interact with a webpage (e.g., click a button, fill out a form, etc.).
+_WEB_DESCRIPTION = """Read (convert to markdown) content from a webpage. You should prefer using the `web_read` tool over the `browser` tool, but do use the `browser` tool if you need to interact with a webpage (e.g., click a button, fill out a form, etc.).

-You may use the `webpage_read` tool to read content from a webpage, and even search the webpage content using a Google search query (e.g., url=`https://www.google.com/search?q=YOUR_QUERY`).
+You may use the `web_read` tool to read content from a webpage, and even search the webpage content using a Google search query (e.g., url=`https://www.google.com/search?q=YOUR_QUERY`).
 """

 WebReadTool = ChatCompletionToolParam(
@@ -49,7 +49,7 @@ class AppConfig:
    default_agent: str = OH_DEFAULT_AGENT
    sandbox: SandboxConfig = field(default_factory=SandboxConfig)
    security: SecurityConfig = field(default_factory=SecurityConfig)
-    runtime: str = 'eventstream'
+    runtime: str = 'docker'
    file_store: str = 'memory'
    file_store_path: str = '/tmp/file_store'
    trajectories_path: str | None = None
@@ -249,9 +249,14 @@ def auto_continue_response(
    try_parse: Callable[[Action | None], str] | None = None,
 ) -> str:
    """Default function to generate user responses.
-    Returns 'continue' to tell the agent to proceed without asking for more input.
+    Tell the agent to proceed without asking for more input, or finish the interaction.
    """
-    return 'continue'
+    message = (
+        'Please continue on whatever approach you think is suitable.\n'
+        'If you think you have solved the task, please finish the interaction.\n'
+        'IMPORTANT: YOU SHOULD NEVER ASK FOR HUMAN RESPONSE.\n'
+    )
+    return message


 if __name__ == '__main__':
@@ -224,7 +224,7 @@ IN_CONTEXT_LEARNING_EXAMPLE_SUFFIX = """
 --------------------- END OF NEW TASK DESCRIPTION ---------------------

 PLEASE follow the format strictly! PLEASE EMIT ONE AND ONLY ONE FUNCTION CALL PER MESSAGE.
-""".lstrip()
+"""

 # Regex patterns for function call parsing
 FN_REGEX_PATTERN = r'<function=([^>]+)>\n(.*?)</function>'
@@ -359,7 +359,9 @@ class LLM(RetryMixin, DebugMixin):
            # noinspection PyBroadException
            except Exception:
                pass
-        logger.debug(f'Model info: {self.model_info}')
+        from openhands.core.utils import json
+
+        logger.debug(f'Model info: {json.dumps(self.model_info, indent=2)}')

        if self.config.model.startswith('huggingface'):
            # HF doesn't support the OpenAI default value for top_p (1)
@@ -182,7 +182,7 @@ async def process_issue(

    config = AppConfig(
        default_agent='CodeActAgent',
-        runtime='eventstream',
+        runtime='docker',
        max_budget_per_task=4,
        max_iterations=max_iterations,
        sandbox=SandboxConfig(
@@ -3,13 +3,13 @@
 ## Introduction

 The OpenHands Runtime folder contains the core components responsible for executing actions and managing the runtime environment for the OpenHands project. This README provides an overview of the main components and their interactions.
-You can learn more about how the runtime works in the [EventStream Runtime](https://docs.all-hands.dev/modules/usage/architecture/runtime) documentation.
+You can learn more about how the runtime works in the [Docker Runtime](https://docs.all-hands.dev/modules/usage/architecture/runtime) documentation.

 ## Main Components

-### 1. impl/*runtime.py
+### 1. base.py

-The `impl/*runtime.py` file defines the `Runtime` class, which serves as the primary [interface](./base.py) for agent interactions with the external environment. It handles various operations including:
+The `base.py` file defines the `Runtime` class, which serves as the primary [interface](./base.py) for agent interactions with the external environment. It handles various operations including:

 - Bash sandbox execution
 - Browser interactions
@@ -23,9 +23,16 @@ Key features of the `Runtime` class:
 - Action execution methods for different types of actions (run, read, write, browse, etc.)
 - Abstract methods for file operations (to be implemented by subclasses)

-### 2. action_execution_server.py
+### 2. impl/action_execution/action_execution_client.py
+The `action_execution_client.py` file contains the `ActionExecutionClient` class, which implements the Runtime interface. It is an abstract implementation, meaning
+it still needs to be extended by a concrete implementation to be used.

-The `action_executor_server.py` file contains the `ActionExecutor` class, which is responsible for executing actions received from the OpenHands backend and producing observations. This client runs inside a Docker sandbox.
+This client interacts with an action_execution_server (defined below) via HTTP
+calls to actually perform runtime actions.
+
+### 3. action_execution_server.py
+
+The `action_executor_server.py` file contains the `ActionExecutor` class, which is responsible for executing actions received via the `/execute_action` HTTP endpoint. It returns observations in the HTTP response.

 Key features of the `ActionExecutor` class:
 - Initialization of user environment and bash shell
@@ -33,6 +40,19 @@ Key features of the `ActionExecutor` class:
 - Execution of various action types (bash commands, IPython cells, file operations, browsing)
 - Integration with BrowserEnv for web interactions

+### 4. Other Implementations
+The `./impl/` directory contains a few different Runtime implementations, all of
+which extend the `ActionExecutionClient` class. These implementations
+handle the lifecycle of a Docker container or other environment running the
+ActionExecutor server.
+
+There are currently four implementations:
+* Docker (runs locally in a Docker container)
+* Remote (runs via a custom HTTP API for creating, pausing, resuming, and stopping runtimes in a remote environment)
+* Modal (uses the Modal API)
+* Runloop (uses the Runloop API)
+
+
 ## Workflow Description

 1. **Initialization**:
@@ -76,9 +96,9 @@ Key features of the `ActionExecutor` class:

 ## Runtime Types

-### EventStream Runtime
+### Docker Runtime

-The EventStream Runtime is designed for local execution using Docker containers:
+The Docker Runtime is designed for local execution using Docker containers:

 - Creates and manages a Docker container for each session
 - Executes actions within the container
@@ -1,8 +1,8 @@
 from openhands.core.logger import openhands_logger as logger
-from openhands.runtime.impl.e2b.sandbox import E2BBox
-from openhands.runtime.impl.eventstream.eventstream_runtime import (
-    EventStreamRuntime,
+from openhands.runtime.impl.docker.docker_runtime import (
+    DockerRuntime,
 )
+from openhands.runtime.impl.e2b.sandbox import E2BBox
 from openhands.runtime.impl.modal.modal_runtime import ModalRuntime
 from openhands.runtime.impl.remote.remote_runtime import RemoteRuntime
 from openhands.runtime.impl.runloop.runloop_runtime import RunloopRuntime
@@ -10,8 +10,8 @@ from openhands.runtime.impl.runloop.runloop_runtime import RunloopRuntime

 def get_runtime_cls(name: str):
    # Local imports to avoid circular imports
-    if name == 'eventstream':
-        return EventStreamRuntime
+    if name == 'eventstream' or name == 'docker':
+        return DockerRuntime
    elif name == 'e2b':
        return E2BBox
    elif name == 'remote':
@@ -30,6 +30,6 @@ __all__ = [
    'RemoteRuntime',
    'ModalRuntime',
    'RunloopRuntime',
-    'EventStreamRuntime',
+    'DockerRuntime',
    'get_runtime_cls',
 ]
@@ -0,0 +1,289 @@
+import os
+import tempfile
+import threading
+from abc import abstractmethod
+from pathlib import Path
+from typing import Any
+from zipfile import ZipFile
+
+import requests
+
+from openhands.core.config import AppConfig
+from openhands.core.exceptions import (
+    AgentRuntimeTimeoutError,
+)
+from openhands.events import EventStream
+from openhands.events.action import (
+    ActionConfirmationStatus,
+    BrowseInteractiveAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileEditAction,
+    FileReadAction,
+    FileWriteAction,
+    IPythonRunCellAction,
+)
+from openhands.events.action.action import Action
+from openhands.events.observation import (
+    ErrorObservation,
+    NullObservation,
+    Observation,
+    UserRejectObservation,
+)
+from openhands.events.serialization import event_to_dict, observation_from_dict
+from openhands.events.serialization.action import ACTION_TYPE_TO_CLASS
+from openhands.runtime.base import Runtime
+from openhands.runtime.plugins import PluginRequirement
+from openhands.runtime.utils.request import send_request
+
+
+class ActionExecutionClient(Runtime):
+    """Base class for runtimes that interact with the action execution server.
+
+    This class contains shared logic between DockerRuntime and RemoteRuntime
+    for interacting with the HTTP server defined in action_execution_server.py.
+    """
+
+    def __init__(
+        self,
+        config: AppConfig,
+        event_stream: EventStream,
+        sid: str = 'default',
+        plugins: list[PluginRequirement] | None = None,
+        env_vars: dict[str, str] | None = None,
+        status_callback: Any | None = None,
+        attach_to_existing: bool = False,
+        headless_mode: bool = True,
+    ):
+        self.session = requests.Session()
+        self.action_semaphore = threading.Semaphore(1)  # Ensure one action at a time
+        self._runtime_initialized: bool = False
+        self._vscode_token: str | None = None  # initial dummy value
+        super().__init__(
+            config,
+            event_stream,
+            sid,
+            plugins,
+            env_vars,
+            status_callback,
+            attach_to_existing,
+            headless_mode,
+        )
+
+    @abstractmethod
+    def _get_action_execution_server_host(self) -> str:
+        pass
+
+    def _send_action_server_request(
+        self,
+        method: str,
+        url: str,
+        **kwargs,
+    ) -> requests.Response:
+        """Send a request to the action execution server.
+
+        Args:
+            method: HTTP method (GET, POST, etc.)
+            url: URL to send the request to
+            **kwargs: Additional arguments to pass to requests.request()
+
+        Returns:
+            Response from the server
+
+        Raises:
+            AgentRuntimeError: If the request fails
+        """
+        return send_request(self.session, method, url, **kwargs)
+
+    def check_if_alive(self) -> None:
+        with self._send_action_server_request(
+            'GET',
+            f'{self._get_action_execution_server_host()}/alive',
+            timeout=5,
+        ):
+            pass
+
+    def list_files(self, path: str | None = None) -> list[str]:
+        """List files in the sandbox.
+
+        If path is None, list files in the sandbox's initial working directory (e.g., /workspace).
+        """
+
+        try:
+            data = {}
+            if path is not None:
+                data['path'] = path
+
+            with send_request(
+                self.session,
+                'POST',
+                f'{self._get_action_execution_server_host()}/list_files',
+                json=data,
+                timeout=10,
+            ) as response:
+                response_json = response.json()
+                assert isinstance(response_json, list)
+                return response_json
+        except requests.Timeout:
+            raise TimeoutError('List files operation timed out')
+
+    def copy_from(self, path: str) -> Path:
+        """Zip all files in the sandbox and return as a stream of bytes."""
+
+        try:
+            params = {'path': path}
+            with send_request(
+                self.session,
+                'GET',
+                f'{self._get_action_execution_server_host()}/download_files',
+                params=params,
+                stream=True,
+                timeout=30,
+            ) as response:
+                temp_file = tempfile.NamedTemporaryFile(delete=False)
+                for chunk in response.iter_content(chunk_size=8192):
+                    if chunk:  # filter out keep-alive new chunks
+                        temp_file.write(chunk)
+                return Path(temp_file.name)
+        except requests.Timeout:
+            raise TimeoutError('Copy operation timed out')
+
+    def copy_to(
+        self, host_src: str, sandbox_dest: str, recursive: bool = False
+    ) -> None:
+        if not os.path.exists(host_src):
+            raise FileNotFoundError(f'Source file {host_src} does not exist')
+
+        try:
+            if recursive:
+                with tempfile.NamedTemporaryFile(
+                    suffix='.zip', delete=False
+                ) as temp_zip:
+                    temp_zip_path = temp_zip.name
+
+                with ZipFile(temp_zip_path, 'w') as zipf:
+                    for root, _, files in os.walk(host_src):
+                        for file in files:
+                            file_path = os.path.join(root, file)
+                            arcname = os.path.relpath(
+                                file_path, os.path.dirname(host_src)
+                            )
+                            zipf.write(file_path, arcname)
+
+                upload_data = {'file': open(temp_zip_path, 'rb')}
+            else:
+                upload_data = {'file': open(host_src, 'rb')}
+
+            params = {'destination': sandbox_dest, 'recursive': str(recursive).lower()}
+
+            with self._send_action_server_request(
+                'POST',
+                f'{self._get_action_execution_server_host()}/upload_file',
+                files=upload_data,
+                params=params,
+                timeout=300,
+            ) as response:
+                self.log(
+                    'debug',
+                    f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}. Response: {response.text}',
+                )
+        finally:
+            if recursive:
+                os.unlink(temp_zip_path)
+            self.log(
+                'debug', f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}'
+            )
+
+    def get_vscode_token(self) -> str:
+        if self.vscode_enabled and self._runtime_initialized:
+            if self._vscode_token is not None:  # cached value
+                return self._vscode_token
+            with send_request(
+                self.session,
+                'GET',
+                f'{self._get_action_execution_server_host()}/vscode/connection_token',
+                timeout=10,
+            ) as response:
+                response_json = response.json()
+                assert isinstance(response_json, dict)
+                if response_json['token'] is None:
+                    return ''
+                self._vscode_token = response_json['token']
+                return response_json['token']
+        else:
+            return ''
+
+    def send_action_for_execution(self, action: Action) -> Observation:
+        if isinstance(action, FileEditAction):
+            return self.edit(action)
+
+        # set timeout to default if not set
+        if action.timeout is None:
+            action.timeout = self.config.sandbox.timeout
+
+        with self.action_semaphore:
+            if not action.runnable:
+                return NullObservation('')
+            if (
+                hasattr(action, 'confirmation_state')
+                and action.confirmation_state
+                == ActionConfirmationStatus.AWAITING_CONFIRMATION
+            ):
+                return NullObservation('')
+            action_type = action.action  # type: ignore[attr-defined]
+            if action_type not in ACTION_TYPE_TO_CLASS:
+                raise ValueError(f'Action {action_type} does not exist.')
+            if not hasattr(self, action_type):
+                return ErrorObservation(
+                    f'Action {action_type} is not supported in the current runtime.',
+                    error_id='AGENT_ERROR$BAD_ACTION',
+                )
+            if (
+                getattr(action, 'confirmation_state', None)
+                == ActionConfirmationStatus.REJECTED
+            ):
+                return UserRejectObservation(
+                    'Action has been rejected by the user! Waiting for further user input.'
+                )
+
+            assert action.timeout is not None
+
+            try:
+                with send_request(
+                    self.session,
+                    'POST',
+                    f'{self._get_action_execution_server_host()}/execute_action',
+                    json={'action': event_to_dict(action)},
+                    # wait a few more seconds to get the timeout error from client side
+                    timeout=action.timeout + 5,
+                ) as response:
+                    output = response.json()
+                    obs = observation_from_dict(output)
+                    obs._cause = action.id  # type: ignore[attr-defined]
+            except requests.Timeout:
+                raise AgentRuntimeTimeoutError(
+                    f'Runtime failed to return execute_action before the requested timeout of {action.timeout}s'
+                )
+
+            return obs
+
+    def run(self, action: CmdRunAction) -> Observation:
+        return self.send_action_for_execution(action)
+
+    def run_ipython(self, action: IPythonRunCellAction) -> Observation:
+        return self.send_action_for_execution(action)
+
+    def read(self, action: FileReadAction) -> Observation:
+        return self.send_action_for_execution(action)
+
+    def write(self, action: FileWriteAction) -> Observation:
+        return self.send_action_for_execution(action)
+
+    def browse(self, action: BrowseURLAction) -> Observation:
+        return self.send_action_for_execution(action)
+
+    def browse_interactive(self, action: BrowseInteractiveAction) -> Observation:
+        return self.send_action_for_execution(action)
+
+    def close(self) -> None:
+        self.session.close()
@@ -1,11 +1,6 @@
 import atexit
-import os
-import tempfile
-import threading
 from functools import lru_cache
-from pathlib import Path
 from typing import Callable
-from zipfile import ZipFile

 import docker
 import requests
@@ -14,40 +9,20 @@ import tenacity
 from openhands.core.config import AppConfig
 from openhands.core.exceptions import (
    AgentRuntimeDisconnectedError,
-    AgentRuntimeError,
    AgentRuntimeNotFoundError,
    AgentRuntimeNotReadyError,
-    AgentRuntimeTimeoutError,
 )
 from openhands.core.logger import DEBUG
 from openhands.core.logger import openhands_logger as logger
 from openhands.events import EventStream
-from openhands.events.action import (
-    ActionConfirmationStatus,
-    BrowseInteractiveAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileEditAction,
-    FileReadAction,
-    FileWriteAction,
-    IPythonRunCellAction,
-)
-from openhands.events.action.action import Action
-from openhands.events.observation import (
-    ErrorObservation,
-    NullObservation,
-    Observation,
-    UserRejectObservation,
-)
-from openhands.events.serialization import event_to_dict, observation_from_dict
-from openhands.events.serialization.action import ACTION_TYPE_TO_CLASS
-from openhands.runtime.base import Runtime
 from openhands.runtime.builder import DockerRuntimeBuilder
-from openhands.runtime.impl.eventstream.containers import remove_all_containers
+from openhands.runtime.impl.action_execution.action_execution_client import (
+    ActionExecutionClient,
+)
+from openhands.runtime.impl.docker.containers import remove_all_containers
 from openhands.runtime.plugins import PluginRequirement
 from openhands.runtime.utils import find_available_tcp_port
 from openhands.runtime.utils.log_streamer import LogStreamer
-from openhands.runtime.utils.request import send_request
 from openhands.runtime.utils.runtime_build import build_runtime_image
 from openhands.utils.async_utils import call_sync_from_async
 from openhands.utils.tenacity_stop import stop_if_should_exit
@@ -62,7 +37,7 @@ def remove_all_runtime_containers():
 _atexit_registered = False


-class EventStreamRuntime(Runtime):
+class DockerRuntime(ActionExecutionClient):
    """This runtime will subscribe the event stream.
    When receive an event, it will send the event to runtime-client which run inside the docker environment.

@@ -74,30 +49,6 @@ class EventStreamRuntime(Runtime):
        env_vars (dict[str, str] | None, optional): Environment variables to set. Defaults to None.
    """

-    # Need to provide this method to allow inheritors to init the Runtime
-    # without initting the EventStreamRuntime.
-    def init_base_runtime(
-        self,
-        config: AppConfig,
-        event_stream: EventStream,
-        sid: str = 'default',
-        plugins: list[PluginRequirement] | None = None,
-        env_vars: dict[str, str] | None = None,
-        status_callback: Callable | None = None,
-        attach_to_existing: bool = False,
-        headless_mode: bool = True,
-    ):
-        super().__init__(
-            config,
-            event_stream,
-            sid,
-            plugins,
-            env_vars,
-            status_callback,
-            attach_to_existing,
-            headless_mode,
-        )
-
    def __init__(
        self,
        config: AppConfig,
@@ -117,10 +68,8 @@ class EventStreamRuntime(Runtime):
        self.config = config
        self._host_port = 30000  # initial dummy value
        self._container_port = 30001  # initial dummy value
-        self._vscode_url: str | None = None  # initial dummy value
        self._runtime_initialized: bool = False
        self.api_url = f'{self.config.sandbox.local_runtime_url}:{self._container_port}'
-        self.session = requests.Session()
        self.status_callback = status_callback

        self.docker_client: docker.DockerClient = self._init_docker_client()
@@ -128,14 +77,13 @@ class EventStreamRuntime(Runtime):
        self.runtime_container_image = self.config.sandbox.runtime_container_image
        self.container_name = CONTAINER_NAME_PREFIX + sid
        self.container = None
-        self.action_semaphore = threading.Semaphore(1)  # Ensure one action at a time

        self.runtime_builder = DockerRuntimeBuilder(self.docker_client)

        # Buffer for container logs
        self.log_streamer: LogStreamer | None = None

-        self.init_base_runtime(
+        super().__init__(
            config,
            event_stream,
            sid,
@@ -153,6 +101,9 @@ class EventStreamRuntime(Runtime):
                f'Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}',
            )

+    def _get_action_execution_server_host(self):
+        return self.api_url
+
    async def connect(self):
        self.send_status_message('STATUS$STARTING_RUNTIME')
        try:
@@ -377,26 +328,18 @@ class EventStreamRuntime(Runtime):
        if not self.log_streamer:
            raise AgentRuntimeNotReadyError('Runtime client is not ready.')

-        with send_request(
-            self.session,
-            'GET',
-            f'{self.api_url}/alive',
-            timeout=5,
-        ):
-            pass
+        self.check_if_alive()

    def close(self, rm_all_containers: bool | None = None):
-        """Closes the EventStreamRuntime and associated objects
+        """Closes the DockerRuntime and associated objects

        Parameters:
        - rm_all_containers (bool): Whether to remove all containers with the 'openhands-sandbox-' prefix
        """
+        super().close()
        if self.log_streamer:
            self.log_streamer.close()

-        if self.session:
-            self.session.close()
-
        if rm_all_containers is None:
            rm_all_containers = self.config.sandbox.rm_all_containers

@@ -407,178 +350,6 @@ class EventStreamRuntime(Runtime):
        )
        remove_all_containers(close_prefix)

-    def run_action(self, action: Action) -> Observation:
-        if isinstance(action, FileEditAction):
-            return self.edit(action)
-
-        # set timeout to default if not set
-        if action.timeout is None:
-            action.timeout = self.config.sandbox.timeout
-
-        with self.action_semaphore:
-            if not action.runnable:
-                return NullObservation('')
-            if (
-                hasattr(action, 'confirmation_state')
-                and action.confirmation_state
-                == ActionConfirmationStatus.AWAITING_CONFIRMATION
-            ):
-                return NullObservation('')
-            action_type = action.action  # type: ignore[attr-defined]
-            if action_type not in ACTION_TYPE_TO_CLASS:
-                raise ValueError(f'Action {action_type} does not exist.')
-            if not hasattr(self, action_type):
-                return ErrorObservation(
-                    f'Action {action_type} is not supported in the current runtime.',
-                    error_id='AGENT_ERROR$BAD_ACTION',
-                )
-            if (
-                getattr(action, 'confirmation_state', None)
-                == ActionConfirmationStatus.REJECTED
-            ):
-                return UserRejectObservation(
-                    'Action has been rejected by the user! Waiting for further user input.'
-                )
-
-            assert action.timeout is not None
-
-            try:
-                with send_request(
-                    self.session,
-                    'POST',
-                    f'{self.api_url}/execute_action',
-                    json={'action': event_to_dict(action)},
-                    # wait a few more seconds to get the timeout error from client side
-                    timeout=action.timeout + 5,
-                ) as response:
-                    output = response.json()
-                    obs = observation_from_dict(output)
-                    obs._cause = action.id  # type: ignore[attr-defined]
-            except requests.Timeout:
-                raise AgentRuntimeTimeoutError(
-                    f'Runtime failed to return execute_action before the requested timeout of {action.timeout}s'
-                )
-
-            return obs
-
-    def run(self, action: CmdRunAction) -> Observation:
-        return self.run_action(action)
-
-    def run_ipython(self, action: IPythonRunCellAction) -> Observation:
-        return self.run_action(action)
-
-    def read(self, action: FileReadAction) -> Observation:
-        return self.run_action(action)
-
-    def write(self, action: FileWriteAction) -> Observation:
-        return self.run_action(action)
-
-    def browse(self, action: BrowseURLAction) -> Observation:
-        return self.run_action(action)
-
-    def browse_interactive(self, action: BrowseInteractiveAction) -> Observation:
-        return self.run_action(action)
-
-    # ====================================================================
-    # Implement these methods (for file operations) in the subclass
-    # ====================================================================
-
-    def copy_to(
-        self, host_src: str, sandbox_dest: str, recursive: bool = False
-    ) -> None:
-        if not os.path.exists(host_src):
-            raise FileNotFoundError(f'Source file {host_src} does not exist')
-
-        try:
-            if recursive:
-                # For recursive copy, create a zip file
-                with tempfile.NamedTemporaryFile(
-                    suffix='.zip', delete=False
-                ) as temp_zip:
-                    temp_zip_path = temp_zip.name
-
-                with ZipFile(temp_zip_path, 'w') as zipf:
-                    for root, _, files in os.walk(host_src):
-                        for file in files:
-                            file_path = os.path.join(root, file)
-                            arcname = os.path.relpath(
-                                file_path, os.path.dirname(host_src)
-                            )
-                            zipf.write(file_path, arcname)
-
-                upload_data = {'file': open(temp_zip_path, 'rb')}
-            else:
-                # For single file copy
-                upload_data = {'file': open(host_src, 'rb')}
-
-            params = {'destination': sandbox_dest, 'recursive': str(recursive).lower()}
-
-            with send_request(
-                self.session,
-                'POST',
-                f'{self.api_url}/upload_file',
-                files=upload_data,
-                params=params,
-                timeout=300,
-            ):
-                pass
-
-        except requests.Timeout:
-            raise AgentRuntimeTimeoutError('Copy operation timed out')
-        except Exception as e:
-            raise AgentRuntimeError(f'Copy operation failed: {str(e)}')
-        finally:
-            if recursive:
-                os.unlink(temp_zip_path)
-            self.log(
-                'debug', f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}'
-            )
-
-    def list_files(self, path: str | None = None) -> list[str]:
-        """List files in the sandbox.
-
-        If path is None, list files in the sandbox's initial working directory (e.g., /workspace).
-        """
-
-        try:
-            data = {}
-            if path is not None:
-                data['path'] = path
-
-            with send_request(
-                self.session,
-                'POST',
-                f'{self.api_url}/list_files',
-                json=data,
-                timeout=10,
-            ) as response:
-                response_json = response.json()
-                assert isinstance(response_json, list)
-                return response_json
-        except requests.Timeout:
-            raise TimeoutError('List files operation timed out')
-
-    def copy_from(self, path: str) -> Path:
-        """Zip all files in the sandbox and return as a stream of bytes."""
-
-        try:
-            params = {'path': path}
-            with send_request(
-                self.session,
-                'GET',
-                f'{self.api_url}/download_files',
-                params=params,
-                stream=True,
-                timeout=30,
-            ) as response:
-                temp_file = tempfile.NamedTemporaryFile(delete=False)
-                for chunk in response.iter_content(chunk_size=8192):
-                    if chunk:  # filter out keep-alive new chunks
-                        temp_file.write(chunk)
-                return Path(temp_file.name)
-        except requests.Timeout:
-            raise TimeoutError('Copy operation timed out')
-
    def _is_port_in_use_docker(self, port):
        containers = self.docker_client.containers.list()
        for container in containers:
@@ -598,27 +369,9 @@ class EventStreamRuntime(Runtime):

    @property
    def vscode_url(self) -> str | None:
-        if self.vscode_enabled and self._runtime_initialized:
-            if (
-                hasattr(self, '_vscode_url') and self._vscode_url is not None
-            ):  # cached value
-                return self._vscode_url
-
-            with send_request(
-                self.session,
-                'GET',
-                f'{self.api_url}/vscode/connection_token',
-                timeout=10,
-            ) as response:
-                response_json = response.json()
-                assert isinstance(response_json, dict)
-                if response_json['token'] is None:
-                    return None
-                self._vscode_url = f'http://localhost:{self._host_port + 1}/?tkn={response_json["token"]}&folder={self.config.workspace_mount_path_in_sandbox}'
-                self.log(
-                    'debug',
-                    f'VSCode URL: {self._vscode_url}',
-                )
-                return self._vscode_url
-        else:
+        token = super().get_vscode_token()
+        print('got token', token)
+        if not token:
            return None
+        vscode_url = f'http://localhost:{self._host_port + 1}/?tkn={token}&folder={self.config.workspace_mount_path_in_sandbox}'
+        return vscode_url
@@ -1,8 +1,7 @@
 import os
 import tempfile
-import threading
 from pathlib import Path
-from typing import Callable, Generator
+from typing import Callable

 import modal
 import requests
@@ -10,9 +9,8 @@ import tenacity

 from openhands.core.config import AppConfig
 from openhands.events import EventStream
-from openhands.runtime.impl.eventstream.eventstream_runtime import (
-    EventStreamRuntime,
-    LogStreamer,
+from openhands.runtime.impl.action_execution.action_execution_client import (
+    ActionExecutionClient,
 )
 from openhands.runtime.plugins import PluginRequirement
 from openhands.runtime.utils.command import get_remote_startup_command
@@ -21,52 +19,13 @@ from openhands.runtime.utils.runtime_build import (
    prep_build_folder,
 )
 from openhands.utils.async_utils import call_sync_from_async
+from openhands.utils.tenacity_stop import stop_if_should_exit

 # FIXME: this will not work in HA mode. We need a better way to track IDs
 MODAL_RUNTIME_IDS: dict[str, str] = {}


-# Modal's log generator returns strings, but the upstream LogBuffer expects bytes.
-def bytes_shim(string_generator) -> Generator[bytes, None, None]:
-    for line in string_generator:
-        yield line.encode('utf-8')
-
-
-class ModalLogStreamer(LogStreamer):
-    """Streams Modal sandbox logs to stdout.
-
-    This class provides a way to stream logs from a Modal sandbox directly to stdout
-    through the provided logging function.
-    """
-
-    def __init__(
-        self,
-        sandbox: modal.Sandbox,
-        logFn: Callable,
-    ):
-        self.log = logFn
-        self._stop_event = threading.Event()
-        self.log_generator = bytes_shim(sandbox.stderr)
-
-        # Start the stdout streaming thread
-        self.stdout_thread = threading.Thread(target=self._stream_logs)
-        self.stdout_thread.daemon = True
-        self.stdout_thread.start()
-
-    def _stream_logs(self):
-        """Stream logs from the Modal sandbox."""
-        try:
-            for log_line in self.log_generator:
-                if self._stop_event.is_set():
-                    break
-                if log_line:
-                    decoded_line = log_line.decode('utf-8').rstrip()
-                    self.log('debug', f'[inside sandbox] {decoded_line}')
-        except Exception as e:
-            self.log('error', f'Error streaming modal logs: {e}')
-
-
-class ModalRuntime(EventStreamRuntime):
+class ModalRuntime(ActionExecutionClient):
    """This runtime will subscribe the event stream.

    When receive an event, it will send the event to runtime-client which run inside the Modal sandbox environment.
@@ -116,14 +75,9 @@ class ModalRuntime(EventStreamRuntime):
        # This value is arbitrary as it's private to the container
        self.container_port = 3000

-        self.session = requests.Session()
        self.status_callback = status_callback
        self.base_container_image_id = self.config.sandbox.base_container_image
        self.runtime_container_image_id = self.config.sandbox.runtime_container_image
-        self.action_semaphore = threading.Semaphore(1)  # Ensure one action at a time
-
-        # Buffer for container logs
-        self.log_streamer: LogStreamer | None = None

        if self.config.sandbox.runtime_extra_deps:
            self.log(
@@ -131,7 +85,7 @@ class ModalRuntime(EventStreamRuntime):
                f'Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}',
            )

-        self.init_base_runtime(
+        super().__init__(
            config,
            event_stream,
            sid,
@@ -170,7 +124,6 @@ class ModalRuntime(EventStreamRuntime):

            self.send_status_message('STATUS$CONTAINER_STARTED')

-        self.log_streamer = ModalLogStreamer(self.sandbox, self.log)
        if self.sandbox is None:
            raise Exception('Sandbox not initialized')
        tunnel = self.sandbox.tunnels()[self.container_port]
@@ -187,6 +140,20 @@ class ModalRuntime(EventStreamRuntime):
        if not self.attach_to_existing:
            self.send_status_message(' ')

+    def _get_action_execution_server_host(self):
+        return self.api_url
+
+    @tenacity.retry(
+        stop=tenacity.stop_after_delay(120) | stop_if_should_exit(),
+        retry=tenacity.retry_if_exception_type(
+            (ConnectionError, requests.exceptions.ConnectionError)
+        ),
+        reraise=True,
+        wait=tenacity.wait_fixed(2),
+    )
+    def _wait_until_alive(self):
+        self.check_if_alive()
+
    def _get_image_definition(
        self,
        base_container_image_id: str | None,
@@ -292,11 +259,7 @@ echo 'export INPUTRC=/etc/inputrc' >> /etc/bash.bashrc

    def close(self):
        """Closes the ModalRuntime and associated objects."""
-        if self.log_streamer:
-            self.log_streamer.close()
-
-        if self.session:
-            self.session.close()
+        super().close()

        if not self.attach_to_existing and self.sandbox:
            self.sandbox.terminate()
@@ -1,10 +1,6 @@
 import os
-import tempfile
-import threading
-from pathlib import Path
 from typing import Callable, Optional
 from urllib.parse import urlparse
-from zipfile import ZipFile

 import requests
 import tenacity
@@ -15,29 +11,13 @@ from openhands.core.exceptions import (
    AgentRuntimeError,
    AgentRuntimeNotFoundError,
    AgentRuntimeNotReadyError,
-    AgentRuntimeTimeoutError,
    AgentRuntimeUnavailableError,
 )
 from openhands.events import EventStream
-from openhands.events.action import (
-    BrowseInteractiveAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileEditAction,
-    FileReadAction,
-    FileWriteAction,
-    IPythonRunCellAction,
-)
-from openhands.events.action.action import Action
-from openhands.events.observation import (
-    ErrorObservation,
-    NullObservation,
-    Observation,
-)
-from openhands.events.serialization import event_to_dict, observation_from_dict
-from openhands.events.serialization.action import ACTION_TYPE_TO_CLASS
-from openhands.runtime.base import Runtime
 from openhands.runtime.builder.remote import RemoteRuntimeBuilder
+from openhands.runtime.impl.action_execution.action_execution_client import (
+    ActionExecutionClient,
+)
 from openhands.runtime.plugins import PluginRequirement
 from openhands.runtime.utils.command import get_remote_startup_command
 from openhands.runtime.utils.request import (
@@ -49,7 +29,7 @@ from openhands.utils.async_utils import call_sync_from_async
 from openhands.utils.tenacity_stop import stop_if_should_exit


-class RemoteRuntime(Runtime):
+class RemoteRuntime(ActionExecutionClient):
    """This runtime will connect to a remote oh-runtime-client."""

    port: int = 60000  # default port for the remote runtime client
@@ -65,10 +45,6 @@ class RemoteRuntime(Runtime):
        attach_to_existing: bool = False,
        headless_mode: bool = True,
    ):
-        # We need to set session and action_semaphore before the __init__ below, or we get odd errors
-        self.session = requests.Session()
-        self.action_semaphore = threading.Semaphore(1)
-
        super().__init__(
            config,
            event_stream,
@@ -98,7 +74,9 @@ class RemoteRuntime(Runtime):
        self.runtime_id: str | None = None
        self.runtime_url: str | None = None
        self._runtime_initialized: bool = False
-        self._vscode_url: str | None = None  # initial dummy value
+
+    def _get_action_execution_server_host(self):
+        return self.runtime_url

    async def connect(self):
        try:
@@ -148,10 +126,9 @@ class RemoteRuntime(Runtime):

    def _check_existing_runtime(self) -> bool:
        try:
-            with self._send_request(
+            with self._send_runtime_api_request(
                'GET',
                f'{self.config.sandbox.remote_runtime_api_url}/sessions/{self.sid}',
-                is_retry=False,
                timeout=60,
            ) as response:
                data = response.json()
@@ -179,10 +156,9 @@ class RemoteRuntime(Runtime):

    def _build_runtime(self):
        self.log('debug', f'Building RemoteRuntime config:\n{self.config}')
-        with self._send_request(
+        with self._send_runtime_api_request(
            'GET',
            f'{self.config.sandbox.remote_runtime_api_url}/registry_prefix',
-            is_retry=False,
            timeout=60,
        ) as response:
            response_json = response.json()
@@ -210,10 +186,9 @@ class RemoteRuntime(Runtime):
            force_rebuild=self.config.sandbox.force_rebuild_runtime,
        )

-        with self._send_request(
+        with self._send_runtime_api_request(
            'GET',
            f'{self.config.sandbox.remote_runtime_api_url}/image_exists',
-            is_retry=False,
            params={'image': self.container_image},
            timeout=60,
        ) as response:
@@ -252,10 +227,9 @@ class RemoteRuntime(Runtime):

        # Start the sandbox using the /start endpoint
        try:
-            with self._send_request(
+            with self._send_runtime_api_request(
                'POST',
                f'{self.config.sandbox.remote_runtime_api_url}/start',
-                is_retry=False,
                json=start_request,
                timeout=60,
            ) as response:
@@ -269,10 +243,9 @@ class RemoteRuntime(Runtime):
            raise AgentRuntimeUnavailableError() from e

    def _resume_runtime(self):
-        with self._send_request(
+        with self._send_runtime_api_request(
            'POST',
            f'{self.config.sandbox.remote_runtime_api_url}/resume',
-            is_retry=False,
            json={'runtime_id': self.runtime_id},
            timeout=60,
        ):
@@ -290,34 +263,19 @@ class RemoteRuntime(Runtime):

    @property
    def vscode_url(self) -> str | None:
-        if self.vscode_enabled and self._runtime_initialized:
-            if (
-                hasattr(self, '_vscode_url') and self._vscode_url is not None
-            ):  # cached value
-                return self._vscode_url
-
-            with self._send_request(
-                'GET',
-                f'{self.runtime_url}/vscode/connection_token',
-                timeout=60,
-            ) as response:
-                response_json = response.json()
-            assert isinstance(response_json, dict)
-            if response_json['token'] is None:
-                return None
-            # parse runtime_url to get vscode_url
-            _parsed_url = urlparse(self.runtime_url)
-            assert isinstance(_parsed_url.scheme, str) and isinstance(
-                _parsed_url.netloc, str
-            )
-            self._vscode_url = f'{_parsed_url.scheme}://vscode-{_parsed_url.netloc}/?tkn={response_json["token"]}&folder={self.config.workspace_mount_path_in_sandbox}'
-            self.log(
-                'debug',
-                f'VSCode URL: {self._vscode_url}',
-            )
-            return self._vscode_url
-        else:
+        token = super().get_vscode_token()
+        if not token:
            return None
+        _parsed_url = urlparse(self.runtime_url)
+        assert isinstance(_parsed_url.scheme, str) and isinstance(
+            _parsed_url.netloc, str
+        )
+        vscode_url = f'{_parsed_url.scheme}://vscode-{_parsed_url.netloc}/?tkn={token}&folder={self.config.workspace_mount_path_in_sandbox}'
+        self.log(
+            'debug',
+            f'VSCode URL: {vscode_url}',
+        )
+        return vscode_url

    def _wait_until_alive(self):
        retry_decorator = tenacity.retry(
@@ -333,7 +291,7 @@ class RemoteRuntime(Runtime):

    def _wait_until_alive_impl(self):
        self.log('debug', f'Waiting for runtime to be alive at url: {self.runtime_url}')
-        with self._send_request(
+        with self._send_runtime_api_request(
            'GET',
            f'{self.config.sandbox.remote_runtime_api_url}/sessions/{self.sid}',
            timeout=60,
@@ -350,12 +308,7 @@ class RemoteRuntime(Runtime):
        # Retry a period of time to give the cluster time to start the pod
        if pod_status == 'ready':
            try:
-                with self._send_request(
-                    'GET',
-                    f'{self.runtime_url}/alive',
-                    timeout=60,
-                ):  # will raise exception if we don't get 200 back.
-                    pass
+                self.check_if_alive()
            except requests.HTTPError as e:
                self.log(
                    'warning', f"Runtime /alive failed, but pod says it's ready: {e}"
@@ -390,182 +343,39 @@ class RemoteRuntime(Runtime):

    def close(self, timeout: int = 10):
        if self.config.sandbox.keep_runtime_alive or self.attach_to_existing:
-            self.session.close()
+            super().close()
            return
-        if self.runtime_id and self.session:
-            try:
-                with self._send_request(
-                    'POST',
-                    f'{self.config.sandbox.remote_runtime_api_url}/stop',
-                    is_retry=False,
-                    json={'runtime_id': self.runtime_id},
-                    timeout=timeout,
-                ):
-                    self.log('debug', 'Runtime stopped.')
-            except Exception as e:
-                raise e
-            finally:
-                self.session.close()
-
-    def run_action(self, action: Action, is_retry: bool = False) -> Observation:
-        if action.timeout is None:
-            action.timeout = self.config.sandbox.timeout
-        if isinstance(action, FileEditAction):
-            return self.edit(action)
-        with self.action_semaphore:
-            if not action.runnable:
-                return NullObservation('')
-            action_type = action.action  # type: ignore[attr-defined]
-            if action_type not in ACTION_TYPE_TO_CLASS:
-                raise ValueError(f'Action {action_type} does not exist.')
-            if not hasattr(self, action_type):
-                return ErrorObservation(
-                    f'[Runtime (ID={self.runtime_id})] Action {action_type} is not supported in the current runtime.',
-                    error_id='AGENT_ERROR$BAD_ACTION',
-                )
-
-            assert action.timeout is not None
-
-            try:
-                request_body = {'action': event_to_dict(action)}
-                self.log('debug', f'Request body: {request_body}')
-                with self._send_request(
-                    'POST',
-                    f'{self.runtime_url}/execute_action',
-                    is_retry=False,
-                    json=request_body,
-                    # wait a few more seconds to get the timeout error from client side
-                    timeout=action.timeout + 5,
-                ) as response:
-                    output = response.json()
-                obs = observation_from_dict(output)
-                obs._cause = action.id  # type: ignore[attr-defined]
-            except requests.Timeout:
-                raise AgentRuntimeTimeoutError(
-                    f'Runtime failed to return execute_action before the requested timeout of {action.timeout}s'
-                )
-            return obs
-
-    def _send_request(self, method, url, is_retry=False, **kwargs):
-        is_runtime_request = self.runtime_url and self.runtime_url in url
        try:
-            return send_request(self.session, method, url, **kwargs)
+            with self._send_runtime_api_request(
+                'POST',
+                f'{self.config.sandbox.remote_runtime_api_url}/stop',
+                json={'runtime_id': self.runtime_id},
+                timeout=timeout,
+            ):
+                self.log('debug', 'Runtime stopped.')
+        except Exception as e:
+            raise e
+        finally:
+            super().close()
+
+    def _send_runtime_api_request(self, method, url, **kwargs):
+        return send_request(self.session, method, url, **kwargs)
+
+    def _send_action_server_request(self, method, url, **kwargs):
+        try:
+            super()._send_action_server_request(method, url, **kwargs)
        except requests.Timeout:
            self.log('error', 'No response received within the timeout period.')
            raise
        except RequestHTTPError as e:
-            if is_runtime_request and e.response.status_code in (404, 502):
+            if e.response.status_code in (404, 502):
                raise AgentRuntimeDisconnectedError(
                    f'{e.response.status_code} error while connecting to {self.runtime_url}'
                ) from e
-            elif is_runtime_request and e.response.status_code == 503:
-                if not is_retry:
-                    self.log('warning', 'Runtime appears to be paused. Resuming...')
-                    self._resume_runtime()
-                    self._wait_until_alive()
-                    return self._send_request(method, url, True, **kwargs)
-                else:
-                    raise AgentRuntimeUnavailableError(
-                        f'{e.response.status_code} error while connecting to {self.runtime_url}'
-                    ) from e
-
+            elif e.response.status_code == 503:
+                self.log('warning', 'Runtime appears to be paused. Resuming...')
+                self._resume_runtime()
+                self._wait_until_alive()
+                return super()._send_action_server_request(method, url, **kwargs)
            else:
                raise e
-
-    def run(self, action: CmdRunAction) -> Observation:
-        return self.run_action(action)
-
-    def run_ipython(self, action: IPythonRunCellAction) -> Observation:
-        return self.run_action(action)
-
-    def read(self, action: FileReadAction) -> Observation:
-        return self.run_action(action)
-
-    def write(self, action: FileWriteAction) -> Observation:
-        return self.run_action(action)
-
-    def browse(self, action: BrowseURLAction) -> Observation:
-        return self.run_action(action)
-
-    def browse_interactive(self, action: BrowseInteractiveAction) -> Observation:
-        return self.run_action(action)
-
-    def copy_to(
-        self, host_src: str, sandbox_dest: str, recursive: bool = False
-    ) -> None:
-        if not os.path.exists(host_src):
-            raise FileNotFoundError(f'Source file {host_src} does not exist')
-
-        try:
-            if recursive:
-                with tempfile.NamedTemporaryFile(
-                    suffix='.zip', delete=False
-                ) as temp_zip:
-                    temp_zip_path = temp_zip.name
-
-                with ZipFile(temp_zip_path, 'w') as zipf:
-                    for root, _, files in os.walk(host_src):
-                        for file in files:
-                            file_path = os.path.join(root, file)
-                            arcname = os.path.relpath(
-                                file_path, os.path.dirname(host_src)
-                            )
-                            zipf.write(file_path, arcname)
-
-                upload_data = {'file': open(temp_zip_path, 'rb')}
-            else:
-                upload_data = {'file': open(host_src, 'rb')}
-
-            params = {'destination': sandbox_dest, 'recursive': str(recursive).lower()}
-
-            with self._send_request(
-                'POST',
-                f'{self.runtime_url}/upload_file',
-                is_retry=False,
-                files=upload_data,
-                params=params,
-                timeout=300,
-            ) as response:
-                self.log(
-                    'debug',
-                    f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}. Response: {response.text}',
-                )
-        finally:
-            if recursive:
-                os.unlink(temp_zip_path)
-            self.log(
-                'debug', f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}'
-            )
-
-    def list_files(self, path: str | None = None) -> list[str]:
-        data = {}
-        if path is not None:
-            data['path'] = path
-
-        with self._send_request(
-            'POST',
-            f'{self.runtime_url}/list_files',
-            is_retry=False,
-            json=data,
-            timeout=30,
-        ) as response:
-            response_json = response.json()
-        assert isinstance(response_json, list)
-        return response_json
-
-    def copy_from(self, path: str) -> Path:
-        """Zip all files in the sandbox and return as a stream of bytes."""
-        params = {'path': path}
-        with self._send_request(
-            'GET',
-            f'{self.runtime_url}/download_files',
-            is_retry=False,
-            params=params,
-            stream=True,
-            timeout=30,
-        ) as response:
-            temp_file = tempfile.NamedTemporaryFile(delete=False)
-            for chunk in response.iter_content(chunk_size=8192):
-                if chunk:  # filter out keep-alive new chunks
-                    temp_file.write(chunk)
-            return Path(temp_file.name)
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Robert Brennan	e0e5792542	minor fixes	2024-12-30 11:48:16 -05:00
Robert Brennan	c17f8a6d68	minor fixes	2024-12-30 11:38:23 -05:00
Robert Brennan	336c5d3c2b	remove isAuthed	2024-12-30 11:35:41 -05:00
Robert Brennan	baf2f766f4	remove null check	2024-12-30 11:34:18 -05:00
Robert Brennan	dfb1731922	fix up settings prompt	2024-12-30 11:32:58 -05:00
Robert Brennan	be497a34ed	return 404 when settings not found	2024-12-30 11:09:23 -05:00
tofarr	4dd40049ab	Refactor ConversationStore to follow SettingsStore pattern (#5881 ) Co-authored-by: openhands <openhands@all-hands.dev>	2024-12-30 09:05:04 -07:00
Cheng Yang	c7a8dcf079	chore(log): better json parse (#5581 )	2024-12-31 00:04:21 +08:00
Vaishakh	2869d646b6	Use i18n Keys (#5286 ) Co-authored-by: openhands <openhands@all-hands.dev> Co-authored-by: amanape <83104063+amanape@users.noreply.github.com>	2024-12-30 15:57:18 +00:00
Robert Brennan	0e4e1b3316	Factor out ActionExecutionClient (#5796 )	2024-12-30 15:32:13 +00:00
dependabot[bot]	37363a0a8d	chore(deps): bump the version-all group across 1 directory with 5 updates (#5914 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: amanape <83104063+amanape@users.noreply.github.com>	2024-12-30 13:19:58 +00:00
OpenHands	14dc04474c	Fix issue #5831 : [Bug]: "Request failed with status code 409" on opening empty repo (#5833 ) Co-authored-by: amanape <83104063+amanape@users.noreply.github.com>	2024-12-30 12:12:31 +00:00
OpenHands	5502a9c448	Fix issue #5806 : Tooltips for navbar (#5807 ) Co-authored-by: Graham Neubig <neubig@gmail.com>	2024-12-30 20:40:06 +09:00
Engel Nyst	e718089802	Fix #5637 : Check for errors in IPython content instead of message (#5895 ) Co-authored-by: openhands <openhands@all-hands.dev>	2024-12-30 12:45:36 +09:00
Boxuan Li	95f7a6a4dc	fn_call_converter: Fix newline in in-context learning prompt (#5903 )	2024-12-29 13:20:05 -08:00
Boxuan Li	7318c22928	web read function call: Fix typo in prompt (#5902 )	2024-12-29 12:14:19 -08:00
mamoodi	78aef2b150	Update headless with no auto continue (#5901 )	2024-12-29 20:10:10 +01:00
Ketan Ramaneti	194181a420	check node.js req for 20.x or later (#5877 )	2024-12-29 11:55:24 +01:00
Rohit Malhotra	2933f07440	[Fix]: Prevent back tick escape (#5897 )	2024-12-29 01:02:14 -05:00
OpenHands	037457dec9	Fix issue #5890 : Add an automatic check of version consistency in documentation (#5891 ) Co-authored-by: Graham Neubig <neubig@gmail.com> Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>	2024-12-29 04:28:47 +00:00
Graham Neubig	7f665c2fb6	Improve test coverage of codeact_agent folder (#5757 ) Co-authored-by: openhands <openhands@all-hands.dev> Co-authored-by: Xingyao Wang <xingyao@all-hands.dev> Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>	2024-12-28 20:12:34 -05:00
Boxuan Li	ebb2d86ce3	Headless or endless? Rewrite auto continue response in headless mode (#5879 )	2024-12-28 10:25:50 -08:00
Boxuan Li	6a4442e590	[Evaluation] Add summarise_results script for TheAgentCompany benchmark (#5811 )	2024-12-27 20:33:41 -08:00
mamoodi	157ff4a4b9	Fix: Prevent submission of empty prompts with spaces (#5874 ) Co-authored-by: openhands <openhands@all-hands.dev>	2024-12-27 15:31:28 -05:00
mamoodi	cc928e6d3f	Fix: Add vertical scrolling to file content viewer (#5872 ) Co-authored-by: openhands <openhands@all-hands.dev>	2024-12-27 15:03:15 -05:00
Robert Brennan	6a75800e1b	fix github auth for settings (#5871 )	2024-12-27 14:15:55 -05:00
tofarr	c9cecbc461	Responsive splash screen (#5864 )	2024-12-27 11:12:48 -07:00
Robert Brennan	97b1867ea1	Fix for settings update (#5858 )	2024-12-27 16:28:11 +00:00
dependabot[bot]	9bdc1df2df	chore(deps): bump boto3 from 1.35.87 to 1.35.88 in the version-all group (#5861 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-12-27 17:15:29 +01:00
sp.wack	9d984aaa30	chore(frontend): Upgrade to React 19 (#5835 )	2024-12-27 19:10:41 +04:00
Boxuan Li	5ed80b5c32	[doc] Fix link in TheAgentCompany benchmark's README.md (#5848 )	2024-12-27 22:21:02 +08:00